MATH211 ProbabilityAndStatistics
Uploaded by
Blah BlahMATH211 ProbabilityAndStatistics
Uploaded by
Blah BlahMAT211: Probability and Statistics1
Dr. Md. Rezaul Karim
PhD(KULeuven & UHasselt), MS(Biostatistics), MS(Statistics)
Associate Professor, Department of Statistics
Jahangirnagar University (JU), Savar, Dhaka - 1342, Bangladesh
Mobile: 01912605556, Email: mrkarim5556sets@iub.edu.bd
Spring - 2023
1
These course slides should not be reproduced nor used by others (without
permission).
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 1 / 463
Lecture Outline I
1 Lecture 1: Introduction
1.1 Problems & Motivation
1.2 Background
1.3 Text and Reference Book List
1.4 What is Statistics?
1.5 Limitation of Statistics
1.6 What is Data?
1.7 Population & Sample
1.8 Variable
1.9 Level or Scales of Measurement
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 2 / 463
Lecture Outline II
1.10 Computer and Statistical packages
1.11 Homework
2 Lecture 2: Summarizing Raw Data
2.1 Frequency Distribution and Relative Frequency Distribution
2.2 Graphical Presentation of data
2.3 Bar Diagram
2.4 Pie Chart
2.5 Homework
3 Lecture - 3: Summarizing Raw Data (Conti...)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 3 / 463
Lecture Outline III
3.1 Line Diagram
3.2 Frequency Polygons
3.3 Ogive or Cumulative Frequency Polygons
3.4 Histogram
3.5 Stem-and-Leaf Plot
3.6 Exercises
3.7 Homework
3.8 Summarizing bivariate data
3.9 Scatter Diagram
3.10 Practice Problem in the Classroom
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 4 / 463
Lecture Outline IV
4 Lecture - 4: Measures of Central Tendency
4.1 Measures of Central Tendency
4.2 Arithmetic Mean
4.3 Geometric Mean
4.4 Harmonic Mean
4.5 Median
4.6 Mode
4.7 Quartiles and Percentiles
4.8 Five-Number summaries and Boxplot
4.9 Boxplots
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 5 / 463
Lecture Outline V
4.10 Exercises
4.11 Homework
5 Lecture - 5: Measures of Dispersion
5.1 Measure of Dispersion
5.2 Absolute Measures
5.3 Relative Measures
5.4 Exercises
5.5 Homework
6 Lecture - 6: Review Class
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 6 / 463
Lecture Outline VI
7 Lecture - 7: Class Test - 1
8 Lecture - 8: Measures of Shape of the Distribution
8.1 Shape of the Distribution
8.2 Skewness
8.3 Mean for grouped data
8.4 Weighted Mean
8.5 Median for Group Data
8.6 Mode for the Group data
8.7 Standard Deviation for Group Data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 7 / 463
Lecture Outline VII
8.8 Homework
9 Lecture - 9: Introduction to probability
9.1 Sample Space and Events
9.2 Events
9.3 Probabilities De ned on Events
9.4 Counting Rules, Combinations, and Permutations
9.5 Approaches Assigning Probabilities
9.6 Homework
10 Lecture - 10: Basic rules for computing probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 8 / 463
Lecture Outline VIII
10.1 Joint and Marginal Probabilities
10.2 Conditional Probability
10.3 Homework
11 Lecture - 11: Review Class
12 Lecture - 12: Mid-term test
13 Lecture 13: Normal Distribution
13.1 Random Variable
13.2 Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 9 / 463
Lecture Outline IX
14 Lecture 14: Standard Normal Distribution
14.1 Standard Normal Probability Distribution
14.2 Homework
15 Lecture 15: Class Test - 2
16 Lecture 16: Random Sampling Methods
16.1 Population & Sample
16.2 Census & Survey
16.3 Sampling Methods
16.4 Simple Random Sampling
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 10 / 463
Lecture Outline X
16.5 How to draw a simple random sample?
17 Lecture 17: Interval estimation
17.1 Interval Estimation
17.2 Con dence interval for µ based on large samples
17.3 Con dence interval for µ based on small samples
17.4 Con dence interval for variance and standard deviation
18 Lecture 18: Interval Estimations about Two Population Means
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 11 / 463
Lecture Outline XI
18.1 Interval Estimation of µ1 − µ2
18.2 Determining the Sample Size
19 Lectures 19: Tests of hypothesis
19.1 Problems & Motivation
19.2 The Null and Alternative Hypotheses
19.3 Key Components of Test of Hypothesis
19.4 The p -value
19.5 Basic Steps for Test of Hypothesis
19.6 Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 12 / 463
Lecture Outline XII
20 Lectures 20: Tests of hypothesis (Conti...)
20.1 Testing on a Single Proportion
21 Lecture 21: Correlation Analysis
21.1 Scatter Diagram
21.2 Covariance
21.3 Correlation Coe cient
21.4 Exercises
21.5 Test for Signi cance Using Correlation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 13 / 463
Lecture Outline XIII
21.6 Homework
22 Lecture 22: Regression Analysis
22.1 Concept of Regression Analysis
22.2 Linear Regression Model
22.3 Homework
23 Lecture 23: Regression Analysis (Conti...)
23.1 Coe cient of Determination (R )
2
23.2 Adjusted R2
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 14 / 463
Lecture Outline XIV
23.3 Homework
24 Lecture 24: Review Class
24.1 Syllabus for the Final Exam and Marks Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 15 / 463
Lecture 1: Introduction
Lecture 1: Introduction
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 16 / 463
Lecture 1: Introduction
1 Lecture 1: Introduction
1.1 Problems & Motivation
1.2 Background
1.3 Text and Reference Book List
1.4 What is Statistics?
1.5 Limitation of Statistics
1.6 What is Data?
1.7 Population & Sample
1.8 Variable
1.9 Level or Scales of Measurement
1.10 Computer and Statistical packages
1.11 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 17 / 463
Lecture 1: Introduction Text and Reference Book List
Text and Reference Book List
Text Book
1 Anderson D. R., Sweeney D. J., and Thomas A. W. (2011): Statistics
for Business & Economics 11th Edition, South-Western, A Division of
Thomson Learning.
Reference list
1 Lind, A. D., Marchal, W. and Wathen, S. (2019): Statistical
Techniques in Business and Economics, 17th Edition, McGraw Hill
Inc.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 18 / 463
Lecture 1: Introduction Text and Reference Book List
Motivation Examples to Study the Course
MATH211: Probability & Statistics
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 19 / 463
Lecture 1: Introduction Text and Reference Book List
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 20 / 463
Lecture 1: Introduction Text and Reference Book List
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 21 / 463
Lecture 1: Introduction Text and Reference Book List
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 22 / 463
Lecture 1: Introduction Text and Reference Book List
graphical presentation of the 4th T20 Bangladesh vs Australia
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 23 / 463
Lecture 1: Introduction Text and Reference Book List
Budget of Bangladesh in 2022 2023
source: https://www.newagebd.net/article/172787/
big-budget-with-high-bank-borrowing-proposed
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 24 / 463
Lecture 1: Introduction Text and Reference Book List
Problems & Motivation
1 from long-term experience, a factory owner knows that a worker can
produce a product in an average time of 89 min. however, on Sunday
morning, there is the impression that it takes longer. how do you
justify whether this impression is correct or not?
2 is there any association between smoking habit and Myocardial
Infarction (MI)?
Myocardial Infarction
Smoking Heart attack No heart attack total
Smoker 325 175 500
Non-smoker 175 325 500
total 500 500 1000
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 25 / 463
Lecture 1: Introduction Text and Reference Book List
Problems & Motivation
3 do temperature and humidity aect the transmission of SARS-CoV-2?
seehttps:
//link.springer.com/article/10.1007/s40745-021-00351-y
4 eect of coee drinking on cancer
the scientist want to see the
disease and they may assume that coee drinking increases the risk of
cancer in humans
how do you justify these hypotheses?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 26 / 463
Lecture 1: Introduction Text and Reference Book List
Chapter-1: Introduction to
Statistics
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 27 / 463
Lecture 1: Introduction What is Statistics?
What is Statistics??
. Statistics
▸ it is a science of data collection, organization, summarization,
classi cation, comparison and drawing of inferences about the
population
▸ is a backbone of data science and is the art of learning from data
▸ it is concerned with the collection of data, its subsequent description
with presentation and its analysis, which often leads to the drawing of
conclusions
▸ also provides tools for prediction and forecasting using data and
statistical models
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 28 / 463
Lecture 1: Introduction What is Statistics?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 29 / 463
Lecture 1: Introduction What is Statistics?
The Scope of Modern Statistics
molecular biology (analysis of microarray data)
ecology (describing quantitatively how individuals in various animal
and plant populations are spatially distributed)
materials engineering (studying properties of various treatments to
retard corrosion)
marketing (developing market surveys and strategies for marketing
new products)
public health (identifying sources of diseases and ways to treat them)
civil engineering (assessing the eects of stress on structural elements
and the impacts of tra c ows on communities)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 30 / 463
Lecture 1: Introduction Limitation of Statistics
Limitation of Statistics
Any Limitation!
statistics is always not suited to the study of qualitative phenomenon
statistics does not study individuals
statistical laws are not exact
statistics is liable to be misused
privacy???
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 31 / 463
Lecture 1: Introduction What is Data?
What is Data?
Data
data are individual units of information
these facts and gures are collected, analyzed, and summarized for
presentation and interpretation
all the data collected in a particular study are referred to as the data
set for the study
Datum
datum (a singular form of "data") is a single piece of information
Raw data
data are collected by survey, census etc.
it is known as ungrouped data
Note: Always we have raw data. We have to process or make data
summaries by various statistical techniques (we will learn all by Chapters
2-3).
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 32 / 463
Lecture 1: Introduction What is Data?
Types of data
1 quantitative data ex: Family size, Score, Age
▸ discrete data ex: family size, whole number
▸ continuous data ex: Score, Age
2 qualitative data (also called categorical data)ex: Gender, Grade, ID
number, cell number
▸ nominal-level data
▸ ordinal-level data
Types of data based on sources
1 primary data
2 secondary data
Types of data based on the purposes of statistical analysis
1 time series data
2 cross-sectional data
3 Pooled data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 33 / 463
Lecture 1: Introduction What is Data?
for the purpose of statistical analysis, distinguishing time series data and
cross-sectional data are meaningful
1 cross-sectional data
▸ are data collected at the same or approximately the same point in time
for example, company's pro t, students pro le we collect at the
same time
Note: in this course most of the data will be considered as cross-sectional
data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 34 / 463
Lecture 1: Introduction What is Data?
the data in Table 1.1 are cross-sectional because they describe the
ve variables for the 25 mutual funds at the same point in time
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 35 / 463
Lecture 1: Introduction What is Data?
2 time series data
▸ are data collected at dierent points in time
for example, Exchange rate, interest rate, gross national product
(GNP), gross domestic product (GDP) and many others
▸ is a series of data points indexed in time order
▸ for example, the time series in Figure 1.1 shows the U.S. average price
per gallon of conventional regular gasoline between 2012 and 2018
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 36 / 463
Lecture 1: Introduction What is Data?
3 pooled data
▸ A combination of time series data and cross-sectional data
▸ one example is GNP per capita of all European countries over ten years
Elements
elements are the entities on which data are collected
if variable is denoted by X, then elements are x1 , x2 , . . . , xn
For the data set in Table 1.1 each individual mutual fund is an
element: the element names appear in the rst column. With 25
mutual funds, the data set contains 25 elements.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 37 / 463
Lecture 1: Introduction Population & Sample
Population and Sample
Target Population (usually, we refer to it as a population in
statistics)
▸ is the aggregate of all possible values of a variable or all possible
objects whose characteristics are of interest in any particular research
Sample
▸ is a part of the target population
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 38 / 463
Lecture 1: Introduction Population & Sample
Random Sample
▸ is a representative part of the target population which has been drawn
randomly
Census
▸ method to collect data on the entire population
▸ As per as 2022 census, Bangladesh have a population of 165,158,616
people, of which 81,712,824 are male, while 83,347,206 are female. As
many as 113,063,587 of them live in rural areas and 52,009,072 live in
Urban.
Sample survey
▸ method for collecting data about the random sample
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 39 / 463
Lecture 1: Introduction Population & Sample
Statistical methods
can be used to summarize or describe a collection of statistical
methods statistics data; this is called descriptive statistics
allows to make predictions (inferences ) from that data; this is called
inferential statistics
Parameter & Statistic
measurable of a population characteristics ⇒ parameter
measurable of a sample characteristics ⇒ statistic
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 40 / 463
Lecture 1: Introduction Variable
Variable & it's types
Variable
. is a characteristics of interest for the elements
. it is also called feature, or factor that vary or change respondent to
respondent
. denoted by X, Y , Z, or denoted by rst letter (e.g., Score (S ), Age
(A))
Types of Variable
1 qualitative variable (also known as categorical variable)
2 quantitative variable (also known as numerical variable)
▸ discrete variable
▸ continuous variable
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 41 / 463
Lecture 1: Introduction Variable
Types of Variable with Examples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 42 / 463
Lecture 1: Introduction Level or Scales of Measurement
Level or Scales of Measurement
level of measurement or scale of measure is a classi cation that describes
the nature of information within the values assigned to variables
1 nominal
2 ordinal
3 interval
4 ratio
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 43 / 463
Lecture 1: Introduction Level or Scales of Measurement
Please read page 6 of the textbook for details.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 44 / 463
Lecture 1: Introduction Level or Scales of Measurement
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 45 / 463
Lecture 1: Introduction Level or Scales of Measurement
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 46 / 463
Lecture 1: Introduction Level or Scales of Measurement
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 47 / 463
Lecture 1: Introduction Level or Scales of Measurement
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 48 / 463
Lecture 1: Introduction Computer and Statistical packages
Computer and Statistical packages
Statistical analyses generally involve a large amount of data. That's why
analysis frequently uses computer software. Several very useful software
are available in computing literature. These are:
Minitab
Excel
R language
MATLAB
Strata
SPSS, and many others.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 49 / 463
Lecture 1: Introduction Homework
Homework
HW: Read Chapter 1 of the text book
Exercises: 2, 4, 6, 9-13, Pages 21-23
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 50 / 463
Lecture 1: Introduction Homework
Chapter-2: Descriptive Statistics:
Tabular and Graphical
Presentations
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 51 / 463
Lecture 2: Summarizing Raw Data
Lecture 2: Summarizing Raw Data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 52 / 463
Lecture 2: Summarizing Raw Data
2 Lecture 2: Summarizing Raw Data
2.1 Frequency Distribution and Relative Frequency Distribution
2.2 Graphical Presentation of data
2.3 Bar Diagram
2.4 Pie Chart
2.5 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 53 / 463
Lecture 2: Summarizing Raw Data
Summarizing Raw Data
Summarizing Categorical Data Summarizing Quantitative Data
Frequency Distribution Frequency Distribution
Relative Frequency Relative Frequency (with
Percent Frequency Distributions percentages)
Bar Diagram or Charts Cumulative Distributions
Pie Charts Line Diagram
Dot Plot
Histogram
Ogive
stem-and-leaf plot and
so on
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 54 / 463
Lecture 2: Summarizing Raw Data Frequency Distribution and Relative Frequency Distribution
Frequency Distribution
a frequency distribution is a tabular summary of data showing the number
(frequency) of items in each of several nonoverlapping classes
Relative frequency (rfi ) = frequency(fi ) ÷ number of observations (n)
Example: Suppose we have 15 students ll out a questionnaire. One of
the questions was, what was the score of your MATH211 course? The
data are following
Make a tabular and graphical summary of the above data.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 55 / 463
Lecture 2: Summarizing Raw Data Frequency Distribution and Relative Frequency Distribution
Solution:
where relative frequency (rfi = fi /n) and percent frequency distribution
(pfi = rfi × 100)
Summary: There are 6 students whose performances are excellent, 5
students show good performance and so on. There are 40% students
performances are excellent, 33% percent are good and so on.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 56 / 463
Lecture 2: Summarizing Raw Data Graphical Presentation of data
Data Presentation
Types of diagram/chart:
. bar diagram
. pie diagram
. line diagram
. frequency polygon
. cumulative frequency polygon or Ogive
. histogram
. stem-and-leaf plot
. box plot
. scatter diagram
. ⋯
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 57 / 463
Lecture 2: Summarizing Raw Data Bar Diagram
Bar Diagram
bar diagram (also called bar chart) is a graphical device for displaying
categorical data summarized in a frequency, relative frequency, or percent
frequency distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 58 / 463
Lecture 2: Summarizing Raw Data Bar Diagram
Bar Diagram (Cont...)
we can use bar diagrams to show the relative sizes of many things, such as
what type of car people have, how many customers a shop has on dierent
days and so on.frequencies
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 59 / 463
Lecture 2: Summarizing Raw Data Pie Chart
Pie Chart (Cont...)
a pie Chart (also called pie diagram) is a special chart that uses "pie
slices" to show relative sizes of data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 60 / 463
Lecture 2: Summarizing Raw Data Pie Chart
Pie Chart (Cont...)
Category frequency (fi ) Angle = fi
∑i fi
× 360○
Comedy 4 72
Action 5 90
Romance 6 108
Drama 1 18
SciFi 4 72
Total ∑i fi = 20
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 61 / 463
Lecture 2: Summarizing Raw Data Pie Chart
Example
Back to the rst example : Suppose we have 15 students ll out a
questionnaire. One of the questions was, what was the score of your
MATH211 course? The data are following
Make a tabular and graphical summary of the above data.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 62 / 463
Lecture 2: Summarizing Raw Data Pie Chart
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 63 / 463
Lecture 2: Summarizing Raw Data Pie Chart
How to Construct a Frequency Distribution?
Steps for constructing a frequency table:
Step 1: Sort the data in ascending order
Step 2: Find minimum and maximum observation of data
Step 3: Decide on the number of classes (k ) in the frequency distribution
k = 1 + 3.322 log(n) or choose k such that 2
k
≥n
Step 4: Determine the class interval (h) size
Maximum observation - Minimum observation
h≥
Number of class (k)
Step 5: Decide the starting point: the lower class limit or class boundary
should cover the smallest value in the raw data.
Step 6: Tally and count the observations under each interval
Relative frequency (rfi ) = frequency(fi ) ÷ number of observations (n)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 65 / 463
Lecture 2: Summarizing Raw Data Pie Chart
Example
Let's take an example to understand how to construct a frequency
distribution. Suppose we have a weekly expenditure of 30 students.
Constructing a frequency distribution table for the following numbers of
observations:
423, 369, 387, 411, 393, 394, 371, 377, 389, 409, 392, 408, 431, 401, 363,
391, 405, 382, 400, 381, 399, 415, 428, 422, 396, 372, 410, 419, 386, 390
1 Step 1: sort data in ascending order
363 369 371 372 377 381 382 386 387 389 390 391 392 393 394
396 399 400 401 405 408 409 410 411 415 419 422 423 428 431
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 66 / 463
Lecture 2: Summarizing Raw Data Pie Chart
2 Step 2:
Minimum Observation is 363 and maximum observation is 431
3 Step 3: Number of classes
k = 1 + 3.322 log(30) = 5.907 ≈ 6
4 Step 4:
Maximum observation - Minimum observation
h≥
Number of class
431 − 363
≥ = 11.33 ≈ 12
6
5 Step 5: Decide the staring point 360
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 67 / 463
Lecture 2: Summarizing Raw Data Pie Chart
Frequency Distribution Table
Therefore, the distribution of weekly expenditure of 30 students is the
following.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 68 / 463
Lecture 2: Summarizing Raw Data Pie Chart
Supplementary Exercises
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 69 / 463
Lecture 2: Summarizing Raw Data Pie Chart
Frequency Distribution with Open-End Classes
Open-ended classes: there are the classes in which either the lower
limit of the rst class is not given or the upper limit of the last class is
not given or the upper limit of the last class is not given or both are
not given
a distribution with open-ended classes is known as frequency
distribution with open end classes.
example:
▸ in the rst class, lower limit is not given
▸ in the last class, upper limit is not given
▸ both these classes are open end classes
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 70 / 463
Lecture 2: Summarizing Raw Data Pie Chart
Practice Problem in the Classroom
Suppose we select 15 students. Their scores of MAT101 are the following:
Table: Test score of MAT 101
90 88 78
87 69 93
56 78 57
67 85 46
95 59 89
Summarize these data by using frequency distribution and comments on it.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 71 / 463
Lecture 2: Summarizing Raw Data Pie Chart
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 72 / 463
Lecture 2: Summarizing Raw Data Homework
Homework
HW: Read related text in Chapter 2 of the text book
Exercises: 4-10, pp.36-39
Exercises: 15-21, pp.46-48
Exercises: 39, 41, 42, pp.65-67
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 73 / 463
Lecture - 3: Summarizing Raw Data (Conti...)
Lecture - 3: Summarizing Raw Data (Conti...)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 74 / 463
Lecture - 3: Summarizing Raw Data (Conti...)
3 Lecture - 3: Summarizing Raw Data (Conti...)
3.1 Line Diagram
3.2 Frequency Polygons
3.3 Ogive or Cumulative Frequency Polygons
3.4 Histogram
3.5 Stem-and-Leaf Plot
3.6 Exercises
3.7 Homework
3.8 Summarizing bivariate data
3.9 Scatter Diagram
3.10 Practice Problem in the Classroom
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 75 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Line Diagram
Line Diagram
a line diagram is a graph that shows related information by drawing a
continuous line between all the points on a grid (usually, as change over
time)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 76 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Line Diagram
Example of Line Diagram
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 77 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Frequency Polygons
Frequency Polygons
a frequency polygon is a graph constructed by using lines to join the
midpoints of each class interval. The heights of the points represent the
frequencies.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 78 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Ogive or Cumulative Frequency Polygons
Cumulative Frequency Polygons (also called Ogive)
graphical presentation of the 4th T20 Bangladesh vs Australia
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 79 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Ogive or Cumulative Frequency Polygons
Remember: Frequency Distribution Table
Remember the last class, the distribution of weekly expenditure of 30
students is the following:
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 80 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Ogive or Cumulative Frequency Polygons
Ogive or Cumulative Frequency Polygons
a ogive is a graph whose vertices represent cumulative frequency of
the data
it is a cumulative distribution graph in which the horizontal axis
represents data values, and the vertical axis represents cumulative
relative frequencies, cumulative frequencies, or cumulative percent
frequencies
How do you interpret these plots?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 81 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Histogram
Bar Diagram vs Histogram
a histogram is a graphical display of data using bars of dierent class
and their frequency
it looks very much like a bar chart, but there are important
dierences between them
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 82 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Histogram
Histogram
to draw a histogram, we sometimes use the mid-value of the class on the
X-axis and frequency (or percentages of relative frequency) on the Y-axis
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 83 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Histogram
Example: Histogram of Two Groups
data about the Basketball teams and the heights of the players
the coach is comparing the heights of his team, the Markwell Cougars
to the rival team, the Sampson Hawks
Markwell Cougars:
170, 172, 175, 176, 176, 176, 178, 181, 182, 183, 183, 183, 185, 185,
187, 188, 188, 189, 190, 195
Sampson Hawks:
169, 175, 176, 176, 178, 179, 180, 183, 183, 186, 186, 186, 187, 187,
187, 187, 187, 188, 190, 191, 192
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 85 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Histogram
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 86 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Histogram
Practice Problem in the Classroom
Suppose we select 15 students. Their scores of MAT101 are the following:
Table: Test score of MAT 101
90 88 78
87 69 93
56 78 57
67 85 46
95 59 89
Summarize these data by using histogram and ogive curve.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 87 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Histogram
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 88 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Histogram
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 89 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Stem-and-Leaf Plot
Stem-and-Leaf Plot
A stem-and-leaf Plot is a special table where each data value is split into a
"stem" (the rst digit or digits) and a "leaf" (usually the last digit). Like
in this example:
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 90 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Stem-and-Leaf Plot
Stem-and-Leaf Plot
the "stem" values are listed down, and the "leaf" values go right (or
left) from the stem values
the "stem" is used to group the scores and each "leaf" shows the
individual scores within each group
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 91 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Stem-and-Leaf Plot
rounding may be needed to create a stem-and-leaf display
based on the following set of data, the stem plot below would be
created:
−23.678758, −12.45, −3.4, 4.43, 5.5, 5.678, 16.87, 24.7, 56.8
for negative numbers, a negative is placed in front of the stem unit,
which is still the value X /10
non-integers are rounded
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 92 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Exercises
Practice Problem in the Classroom
Suppose we select 15 students. Their scores of MAT101 are the following:
Table: Test score of MAT 101
90 88 78
87 69 93
56 78 57
67 85 46
95 59 89
Summarize these data by using stem-and-leaf plot.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 93 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Exercises
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 94 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Exercises
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 95 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Exercises
Supplementary Exercises
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 96 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Exercises
Exercises
1 What do you mean by Statistics? Write down some applications of
Statistics in engineering eld.
2 What is meant by population and sample? Discuss the dierent types
of data.
3 What do you mean by sampling (or sampling technique)? Discuss the
dierent types of sampling technique for selecting a sample.
4 What are the points to be borne in mind in the formation of
frequency table? Choosing appropriate class-intervals, form a
frequency table for the following data:
10.2 0.5 5.2 6.1 3.1 6.7 8.9 7.2 8.9
5.4 3.6 9.2 6.1 7.3 2.0 1.3 6.4 8.0
4.3 4.7 12.4 8.6 13.1 3.2 9.5 7.6 4.0
5.1 8.1 1.1 11.5 3.1 6.8 7.0 8.2 2.0
3.1 6.5 11.2 12.0 5.1 10.9 11.2 8.5 2.3
3.4 5.2 10.7 4.9 6.2
Draw the histogram, frequency curve and stem-and-leaf for the above
data.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 97 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Exercises
Exercises: Ross(2020)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 98 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Homework
Homework
HW: Read related text in Chapter 2 of the text book
Exercises: 15-21, pp.46-48
Exercises: 25-28, pp.52-53 and
Exercises: 31, 33-36, pp.60-61
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 99 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Summarizing bivariate data
Summarizing bivariate data
Tabular Method-Crosstabulation
▸ A tabular summary of data for two variables. The classes for one
variable are represented by the rows; the classes for the other variable
are represented by the columns.
Graphical method- scatter diagram
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 100 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Summarizing bivariate data
Example: Test Performances of MAT 101
ID Gender Test Performance Study Hour Score of STAT
1 Male Good 10 71
2 Female Good 11 75
3 Male Excellent 14 85
4 Female Excellent 10 90
5 Male Poor 8 50
6 Female Excellent 13 88
7 Male Poor 6 45
8 Female Excellent 15 80
9 Male Good 14 65
10 Female Good 10 82
11 Male Excellent 14 92
12 Female Poor 8 55
13 Male Poor 5 40
14 Male Good 10 68
15 Female Good 9 62
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 101 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Summarizing bivariate data
Table: The Crosstabulation of Gender and Test Performance.
Gender Test Performance Total
Poor Good Excellent
Male 3 3 2 8
Female 1 3 3 7
Total 4 6 5 15
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 102 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Summarizing bivariate data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 103 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Scatter Diagram
Scatter Diagram
a scatter diagram is a graphic tool used to display the relationship between
two variables
the dependent variable is scaled on the Y-axis and is the variable
being estimated
the independent variable is scaled on the X-axis and is the variable
used as the predictor
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 104 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Practice Problem in the Classroom
Example: Scatter Diagram of Study Hour and Score
For interpretation, we have to focus on the following points:
Strength
Shape linear, curved etc.
Direction positive or negative
Presence of outliers
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 105 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Practice Problem in the Classroom
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 106 / 463
Lecture - 3: Summarizing Raw Data (Conti...) Practice Problem in the Classroom
Chapter 3: Descriptive Statistics:
Numerical Measures
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 107 / 463
Lecture - 4: Measures of Central Tendency
Lecture - 4: Measures of Central Tendency
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 108 / 463
Lecture - 4: Measures of Central Tendency
4 Lecture - 4: Measures of Central Tendency
4.1 Measures of Central Tendency
4.2 Arithmetic Mean
4.3 Geometric Mean
4.4 Harmonic Mean
4.5 Median
4.6 Mode
4.7 Quartiles and Percentiles
4.8 Five-Number summaries and Boxplot
4.9 Boxplots
4.10 Exercises
4.11 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 109 / 463
Lecture - 4: Measures of Central Tendency
We will learn several numerical measures that provide a data summary
using numeric formulas. Now we will learn the following:
Measures of average: simple mean, weighted mean, median, mode,
quartiles, percentiles
Measures of variation: Range, inter-quartile range, variance, standard
deviation
Measures of skewness: symmetry, positive skewness, negative
skewness
Measures of Kurtosis: leptokurtic, platykurtic and mesokurtic
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 110 / 463
Lecture - 4: Measures of Central Tendency Measures of Central Tendency
A measure of central tendency
Questions
1 How to estimate central value of a population?
2 Would you tell a characteristic which represent whole dataset?
Measure of central tendency
a summary statistic that represents the center point or typical value
of a dataset
the most common measures of central tendency are the
(i). mean
∎ arithmetic mean
∎ harmonic mean
∎ geometric mean
(ii). median
(iii). mode
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 111 / 463
Lecture - 4: Measures of Central Tendency Arithmetic Mean
Arithmetic Mean
Arithmetic mean (AM) (usually refer sample mean)
sum all of the values and divide by the number of observations in your
dataset
the (arithmetic) mean of a set of numbers x1 , x2 , . . . , xn is typically
denoted by x̄ , is the sum of the sampled values divided by the number
of items in the sample
1
n
x1 + x2 + ⋯ + xn
x̄ = (∑ xi ) =
n i=1 n
ex: the arithmetic mean of ve values: 4, 36, 45, 50, 75 is:
x1 + x2 + ⋯ + x5 4 + 36 + 45 + 50 + 75 210
x̄ = = = = 42
5 5 5
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 112 / 463
Lecture - 4: Measures of Central Tendency Geometric Mean
Geometric Mean
Geometric mean (GM)
is an average that is useful for sets of positive numbers that are
interpreted according to their product and not their sum (as is the
case with the arithmetic mean); e.g., rates of growth
1
n n 1
x̄ = (∏ xi ) = (x1 x2 ⋯xn ) n
i= 1
ex: the geometric mean of ve values: 4, 36, 45, 50, 75 is:
1 1 √
5
x̄ = (x1 x2 ⋯x5 ) 5 = (4 × 36 × 45 × 50 × 75) 5 = 24 300 000 = 30
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 113 / 463
Lecture - 4: Measures of Central Tendency Harmonic Mean
Harmonic Mean
Harmonic mean (HM)
is an average which is useful for sets of numbers which are de ned in
relation to some unit, for example speed (distance per unit of time).
n
1
− 1
x̄ = n (∑ )
i= 1 xi
ex: the harmonic mean of the ve values: 4, 36, 45, 50, 75 is
5 − 1
1 5 5
x̄ = 5 (∑ ) = 1 1 1 1 1 = 1 = 15
i= 1 xi 4 + 36 + 45 + 50 + 75 3
Relationship between AM, GM, and HM
AM ≥ GM ≥ HM
equality holds if and only if all the elements of the given sample are equal
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 114 / 463
Lecture - 4: Measures of Central Tendency Harmonic Mean
Practice problem in the Class
1 Consider a sample with data values of 10, 20, 12, 17, and 16.
Compute the arithmetic mean, geometric mean and harmonic mean
and comment on your results.
2 Consider a sample with data values of 10, 20, 12, 17,10, and 16.
Compute the arithmetic mean, geometric mean and harmonic mean
and comment on your results.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 115 / 463
Lecture - 4: Measures of Central Tendency Harmonic Mean
Properties of Arithmetic Mean
it requires at least the interval scale
all values are used
it is unique
it is easy to calculate and allow easy mathematical treatment
the sum of the deviations from the mean is 0
the arithmetic mean is the only measure of central tendency where
the sum of the deviations of each value from the mean is zero!
it is easily aected by extremes, such as very big or small numbers in
the set (non-robust)
...
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 116 / 463
Lecture - 4: Measures of Central Tendency Harmonic Mean
Merits of Mean
rigidly de ned by algebraic formula
easy to calculate and simple to understand
based on all observations of the given data
capable of being treated mathematically hence it is widely used in statistical
analysis
can be computed even if the derailed distribution is not known but some of
the observation and number of the observation are known
least aected by the uctuation of sampling
for every kind of numeric data mean can be calculated
...
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 117 / 463
Lecture - 4: Measures of Central Tendency Harmonic Mean
Demerits of Mean
1 an not be computed for qualitative data like data on intelligence honesty and
smoking habit etc.
2 too much aected by extreme observations and hence it is not adequately
represent data consisting of some extreme point
3 can not be computed when class intervals have open ends
4 if any one of the data is missing then mean can not be calculated
5 ...
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 118 / 463
Lecture - 4: Measures of Central Tendency Median
Median
is the value separating the higher half from the lower half of a data
sample (a population or a probability distribution)
used to nd the index of the middle number of a data set of n
numerically ordered numbers is (n + 1)/2. This either gives the
middle number (for an odd number of values) or the halfway point
between the two middle values
ex: If there is an odd number of numbers, the middle one is picked.
e.g. consider the list of numbers 1, 3, 3, 6, 7, 8, 9. This list contains
seven numbers. The median is the fourth of them, which is 6.
If there is an even number of observations, then there is no single
middle value; the median is then usually de ned to be the mean of the
two middle values. For the data set: 1, 2, 3, 4, 5, 6, 8, 9, the median
is the mean of the middle two numbers: this is (4 + 5)/2, which is 4.5
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 119 / 463
Lecture - 4: Measures of Central Tendency Median
Practice problem in the Class
1 Consider a sample with data values of 10, 20, 12, 17, and 16.
Compute the mean and median.
2 Consider a sample with data values of 10, 20, 12, 17, 10 and 16.
Compute the mean and median.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 120 / 463
Lecture - 4: Measures of Central Tendency Median
Merits of Median
1 easy to calculate and simple to understand
2 well de ned an ideal average should be
3 can also be computed in case of frequency distribution with open
ended classes
4 not aected by extreme values and also interdependent of range or
dispersion of the data
5 can be determined graphically
6 proper average for qualitative data where items are not measured but
are scored
7 only suitable average when the data are qualitative & it is possible to
rank various items according to qualitative characteristics.
8 ...
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 121 / 463
Lecture - 4: Measures of Central Tendency Median
Demerits of Median
1 for computing median data needs to be arranged in ascending or
descending order
2 not based on all the observations of the data
3 can not be given further algebraic treatment
4 aected by uctuation of sampling
5 not accurate when the data size is not large
6 ...
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 122 / 463
Lecture - 4: Measures of Central Tendency Mode
Mode
is simply the number which appears most often
⧫ To nd the mode, or modal value, it is best to put the numbers in order.
hen count how many of each number. A number that appears most often
is the mode.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 123 / 463
Lecture - 4: Measures of Central Tendency Mode
Practice problem in the Classroom
1 Consider a sample with data values of 10, 12, 12, 16, and 18.
Compute the mode.
2 Consider a sample with data values of 10, 12, 12, 16, 16 and 18.
Compute the mode and comments on your results.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 124 / 463
Lecture - 4: Measures of Central Tendency Quartiles and Percentiles
Quartiles and Percentiles
based on their position in a series of observations
not necessarily central values
quartile can be de ned as
n+1
Qk = ( × k) th observation k = 1 , 2, 3
4
percentile can be de ned as
n+1
Pk = ( × k) th observation k = 1, 2, . . . , 99
100
decile can be de ned as
n+1
Dk = ( × k) th observation k = 1, 2, . . . , 9
10
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 125 / 463
Lecture - 4: Measures of Central Tendency Quartiles and Percentiles
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 126 / 463
Lecture - 4: Measures of Central Tendency Quartiles and Percentiles
Example
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 127 / 463
Lecture - 4: Measures of Central Tendency Quartiles and Percentiles
Example
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 128 / 463
Lecture - 4: Measures of Central Tendency Five-Number summaries and Boxplot
Five-Number Summary
in a ve-number summary, ve numbers are used to summarize the data:
1 smallest (or minimum) value
2 rst quartile (Q1 )
3 median (Q2 )
4 third quantile (Q3 )
5 largest (or maximum) value
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 129 / 463
Lecture - 4: Measures of Central Tendency Boxplots
Boxplot
a boxplot is a standardized way of displaying the distribution of data
based on a ve number summary (minimum, rst quartile (Q1),
median, third quartile (Q3), and maximum)
it can tell you about your outliers and what their values are
it can also tell you if your data is symmetrical, how tightly your data
is grouped, and if and how your data is skewed.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 130 / 463
Lecture - 4: Measures of Central Tendency Boxplots
Boxplot
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 131 / 463
Lecture - 4: Measures of Central Tendency Boxplots
Example
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 132 / 463
Lecture - 4: Measures of Central Tendency Boxplots
Example
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 133 / 463
Lecture - 4: Measures of Central Tendency Boxplots
Example
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 134 / 463
Lecture - 4: Measures of Central Tendency Boxplots
Detecting Outliers
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 135 / 463
Lecture - 4: Measures of Central Tendency Boxplots
Example
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 136 / 463
Lecture - 4: Measures of Central Tendency Exercises
What do you think about the following questions?
1 What is meant by central tendency of data? What are the various
measures of central tendency and location? Explain them with
examples.
2 What are the characteristics of ideal central tendency measure?
According to you, what is the ideal central tendency measure and
why?
3 What are appropriate measure of central tendency for nominal and
ordinal data? Which measures of central tendency is applicable at all
levels of measurements? Why?
4 What is a median, quartiles, deciles and percentiles? ? The following
values represent the results of several measurements on the
concentration of calcium in a stream
14, 8, 9, 8, 13, 14, 8, 8, 12, 11, 10, 12, 12
(a). Calculate the mean concentration
(b). Calculate the median and the mode
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 137 / 463
Lecture - 4: Measures of Central Tendency Homework
Homework
Read Course Guide, pp.15-16
HW: Read related text in Chapter 3 of the text book
Exercise: 5-10, pp.92-94
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 138 / 463
Lecture - 5: Measures of Dispersion
Lecture - 5: Measures of Dispersion
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 139 / 463
Lecture - 5: Measures of Dispersion
5 Lecture - 5: Measures of Dispersion
5.1 Measure of Dispersion
5.2 Absolute Measures
5.3 Relative Measures
5.4 Exercises
5.5 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 140 / 463
Lecture - 5: Measures of Dispersion Measure of Dispersion
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 141 / 463
Lecture - 5: Measures of Dispersion Measure of Dispersion
A Measure of Dispersion
Dispersion
. is the state of getting dispersed, i. e. spread of data
. is contrasted with location or central tendency, and together they are
the most used properties of distributions
. the measure which express the scattering of observation in terms of
distances i.e., range, quartile deviation
. the measure which expresses the variations in terms of the average of
deviations of observations like mean deviation and standard deviation
. spread can also be shown in graphs: dot plots, boxplots, and stem
and leaf plots have a greater distance with samples that have a larger
dispersion and vice versa
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 142 / 463
Lecture - 5: Measures of Dispersion Measure of Dispersion
Dierent Measures of Dispersion
Absolute Measures
1 range: maximum value - minimum value
2 interquartile range (IQR): Q3 − Q1
3 semi-interquartile range : (Q3 − Q1 )/2
4 variance (or standard deviation)
5 mean absolute dierence (also known as Gini mean absolute
dierence)
6 median absolute deviation (MAD)
Relative Measures
1 coe cient of variation
2 skewness
3 kurtosis
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 143 / 463
Lecture - 5: Measures of Dispersion Absolute Measures
Absolute Measures
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 144 / 463
Lecture - 5: Measures of Dispersion Absolute Measures
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 145 / 463
Lecture - 5: Measures of Dispersion Absolute Measures
Practice in Classroom
1 Consider a sample with data values of 10, 20, 12, 17, and Compute
the range and interquartile range.
2 Consider a sample with data values of 10, 20, 12, 17, and Compute
the range, interquartile range and Semi-interquartile range.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 146 / 463
Lecture - 5: Measures of Dispersion Absolute Measures
Variance
the variance (and standard deviation) is a measure of how widely
values are dispersed from the average value (the mean)
variance is an average of squared deviation of values from the mean
( µ)
−− usually, population variance is denoted by σ2
−− usually, sample variance is denoted by s
2
where
▸ for population
1 N 2 1 n 2
σ2 = 2
∑ (Xi − µ) = (∑ Xi − Nµ )
N i=1 N i=1
▸ for sample
1 n 2 1 n
s2 = ∑ (xi − x̄) = (∑ xi2 − nx̄ 2 )
n − 1 i=1 n − 1 i=1
advantages & disadvantages?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 147 / 463
Lecture - 5: Measures of Dispersion Absolute Measures
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 148 / 463
Lecture - 5: Measures of Dispersion Absolute Measures
Standard Deviation
is a square root of a variance and sample standard deviation is
denoted by s
for sample
¿ ¿
Á
s =Á
À 1
n
2 Á
∑ (xi − x̄) = Á
À 1
n
(∑ xi2 − nx̄ 2 )
n − 1 i=1 n−1 i= 1
the major characteristics of the standard deviation are:
1 it is in the same units as the original data
2 it is the square root of the average squared distance from the mean
3 it cannot be negative
4 it is the most widely reported measure of dispersion
advantages & disadvantages?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 149 / 463
Lecture - 5: Measures of Dispersion Absolute Measures
Practice in Classroom
1 Consider a sample with data values of 10, 20, 12, 17, and Compute
the range and interquartile range.
2 Consider a sample with data values of 10, 20, 12, 17, and Compute
the variance and standard deviation.
3 Consider a sample with data values of 27, 25, 20, 15, 30, 34, 28, and
25. Compute the range, interquartile range, variance, and standard
deviation.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 150 / 463
Lecture - 5: Measures of Dispersion Absolute Measures
Mean Absolute Deviation
. mean absolute deviation from the average value (the mean)
for sample
n
1
MAD(x̄) = ∑ ∣xi − x̄∣
n i=1
where X̄ and x̄ are respectively, population mean and sample mean
. this measure does not square the distance from the mean, so it is less
aected by extreme observations than are the variance and standard
deviation
. advantages & disadvantages?
. Use data given in Table 3.2, what is Mean Absolute Deviation?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 151 / 463
Lecture - 5: Measures of Dispersion Absolute Measures
Median Absolute Deviation
. mean absolute deviation from the average value (the mean)
▸ for sample
MedAD(x̄) = median∣xi − x̃∣
where X̃ and x̃ are respectively, population mean and sample median
. this measure does not square the distance from the mean, so it is less
aected by extreme observations than are the variance and standard
deviation
. advantages & disadvantages?
. Use data given in Table 3.2, what is Median Absolute Deviation?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 152 / 463
Lecture - 5: Measures of Dispersion Relative Measures
Coe cient of Variation
the coe cient of variation (CV) is a statistical measure of the
dispersion of data points in a data series around the mean
the coe cient of variation represents the ratio of the standard
deviation to the mean, and it is a useful statistic for comparing the
degree of variation from one data series to another, even if the means
are drastically dierent from one another
▸ for sample
s
cv = × 100%
x̄
advantages & disadvantages?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 153 / 463
Lecture - 5: Measures of Dispersion Exercises
Exercises
1 What do you mean by dispersion? What are the dierent measures of
dispersion? Discuss them with a suitable example.
2 What are the relative measures of dispersion? Discuss the importance
of coe cient of variation.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 154 / 463
Lecture - 5: Measures of Dispersion Homework
Homework
Course Guide, pp.17-18
HW: Read related text in Chapter 3 of the text book
Exercise: 16-24, pp.100-102 and
Exercise: 40-41, pp.112-113
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 155 / 463
Lecture - 6: Review Class
Lecture - 6: Review Class
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 156 / 463
Lecture - 6: Review Class
6 Lecture - 6: Review Class
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 157 / 463
Lecture - 7: Class Test - 1
Lecture - 7: Class Test - 1
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 158 / 463
Lecture - 7: Class Test - 1
7 Lecture - 7: Class Test - 1
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 159 / 463
Lecture - 8: Measures of Shape of the Distribution
Lecture - 8: Measures of Shape of the Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 160 / 463
Lecture - 8: Measures of Shape of the Distribution
8 Lecture - 8: Measures of Shape of the Distribution
8.1 Shape of the Distribution
8.2 Skewness
8.3 Mean for grouped data
8.4 Weighted Mean
8.5 Median for Group Data
8.6 Mode for the Group data
8.7 Standard Deviation for Group Data
8.8 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 161 / 463
Lecture - 8: Measures of Shape of the Distribution Shape of the Distribution
Measures of Distribution Shape
shape of the distribution
▸ skewness
▸ kurtosis
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 162 / 463
Lecture - 8: Measures of Shape of the Distribution Shape of the Distribution
Skewness
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 163 / 463
Lecture - 8: Measures of Shape of the Distribution Shape of the Distribution
Shape of the Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 164 / 463
Lecture - 8: Measures of Shape of the Distribution Skewness
Skewness
skewness characterizes the degree of asymmetry of a distribution
around its mean
▸ Fisher-Pearson coe cient of skewness
n n
xi − x̄ 3
skewness: s1 = ∑( )
(n − 1)(n − 2) i=1 s
▸ Pearson median coe cient of skewness
x̄ − median
skewness: s1 = 3 ( )
s
positive skewness indicates a distribution with an asymmetric tail
extending toward more positive values ⇒right skewed distribution
zero indicates a symmetric distribution ⇒mean = median = mode
negative skewness indicates a distribution with an asymmetric tail
extending toward more negative values ⇒ left skewed distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 165 / 463
Lecture - 8: Measures of Shape of the Distribution Skewness
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 166 / 463
Lecture - 8: Measures of Shape of the Distribution Skewness
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 167 / 463
Lecture - 8: Measures of Shape of the Distribution Skewness
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 168 / 463
Lecture - 8: Measures of Shape of the Distribution Skewness
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 169 / 463
Lecture - 8: Measures of Shape of the Distribution Skewness
Kurtosis
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 170 / 463
Lecture - 8: Measures of Shape of the Distribution Skewness
Kurtosis
kurtosis characterizes the relative peakedness or atness of a
distribution compared with the normal distribution
the kurtosis for a normal distribution is 3
in other words, kurtosis identi es whether the tails of a given
distribution contain extreme values
▸ most software packages (including Microsoft Excel) use the formula
below: coe cient of kurtosis (or, excess kurtosis)
n(n + 1) n
xi − x̄ 4 3(n − 1)2
s2 = ∑( ) −
(n − 1)(n − 2)(n − 3) i=1 s (n − 2)(n − 3)
it is also called coe cient of kurtosis (or, excess kurtosis)
Dr. Wheeler de nes kurtosis as:
The kurtosis parameter is a measure of the combined weight of the
tails relative to the rest of the distribution.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 171 / 463
Lecture - 8: Measures of Shape of the Distribution Skewness
Kurtosis
positive kurtosis indicates a relatively peaked distribution ⇒
Leptokurtic
the leptokurtic distribution shows heavy tails on either side, indicating
large outliers
zero indicates a normal distribution ⇒ Mesokurtic
negative kurtosis indicates a relatively at distribution ⇒Platykurtic
the at tails indicate the small outliers in a distribution
advantages & disadvantages?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 172 / 463
Lecture - 8: Measures of Shape of the Distribution Mean for grouped data
Exercises
1 Suppose you have following data:
423, 369, 387, 411, 393, 394, 371, 377, 389, 409, 392, 408, 431, 401,
363, 391, 405, 382, 400, 381, 399, 415, 428, 422, 396, 372, 410, 419,
386, 390.
Draw a frequency distribution table and hence calculate mean,
median and mode.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 173 / 463
Lecture - 8: Measures of Shape of the Distribution Mean for grouped data
for group data:
∑ki=1 fi xi f1 x1 + f2 x2 + ⋯ + fk xk
x̄ = =
∑ki=1 fi ∑ki=1 fi
example:
▸ the weights (in gms) of 30 articles are given below :
14, 16, 16, 14, 22, 13, 15, 24, 23, 14, 20, 17, 21, 18, 18, 19, 20, 17,
16, 15, 11, 22, 21, 20, 17, 18, 19, 22, 23.
▸ form a grouped frequency table, by dividing the variate range into
intervals of equal width, one class being 11-13 and then compute the
arithmetic mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 174 / 463
Lecture - 8: Measures of Shape of the Distribution Mean for grouped data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 175 / 463
Lecture - 8: Measures of Shape of the Distribution Weighted Mean
Weighted Mean
▸▸ the weighted mean is found by multiplying each observation by its
corresponding weight
w1 x1 + w2 x2 + ⋯ + wk xk
x̄w =
w1 + w2 + ⋯ + wk
Self Exercise: Springers sold 95 Antonelli men's suits for the regular price
of $400. For the spring sale, the suits were reduced to $200 and 126 were
sold. At the nal clearance, the price was reduced to $100 and the
remaining 79 suits were sold.
(a). What was the weighted mean price of an Antonelli suit?
(b). Springers paid $200 a suit for the 300 suits. Comment on the store's
pro t per suit if a salesperson receives a $25 commission for each one
sold.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 176 / 463
Lecture - 8: Measures of Shape of the Distribution Weighted Mean
Practice problem in the Classroom
Consider the following data and corresponding weights.
xi weight (wi )
3.2 6
2.0 3
2.5 2
5.0 8
(i). Compute the weighted mean.
(ii). Compute the sample mean of the four data values without weighting.
Note the dierence in the results provided by the two computations.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 177 / 463
Lecture - 8: Measures of Shape of the Distribution Median for Group Data
Median for Group Data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 178 / 463
Lecture - 8: Measures of Shape of the Distribution Median for Group Data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 179 / 463
Lecture - 8: Measures of Shape of the Distribution Median for Group Data
Consider the following data.
Class Interval frequency (fi )
4-6 6
6-8 4
8-10 2
10-12 8
Compute the mean and median.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 180 / 463
Lecture - 8: Measures of Shape of the Distribution Mode for the Group data
Mode for the Group data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 181 / 463
Lecture - 8: Measures of Shape of the Distribution Mode for the Group data
Mode for group data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 182 / 463
Lecture - 8: Measures of Shape of the Distribution Mode for the Group data
Practice problem in the Classroom
1 Consider the following data.
Class Interval frequency (fi )
4-6 6
6-8 4
8-10 2
10-12 8
Compute the mode and comment on your results.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 183 / 463
Lecture - 8: Measures of Shape of the Distribution Standard Deviation for Group Data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 184 / 463
Lecture - 8: Measures of Shape of the Distribution Standard Deviation for Group Data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 185 / 463
Lecture - 8: Measures of Shape of the Distribution Standard Deviation for Group Data
Exercises: Ross(2020)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 186 / 463
Lecture - 8: Measures of Shape of the Distribution Standard Deviation for Group Data
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 187 / 463
Lecture - 8: Measures of Shape of the Distribution Homework
Homework
Course Guide, pp.20-28
HW: Read related text in Chapter 3 of the text book
Exercise: 54-57, pp.128-129 and
Case problems 1, 2, 3, 4, pp.137-141
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 188 / 463
Lecture - 8: Measures of Shape of the Distribution Homework
Chapter - 4: Introduction to
Probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 189 / 463
Lecture - 9: Introduction to probability
Lecture - 9: Introduction to probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 190 / 463
Lecture - 9: Introduction to probability
9 Lecture - 9: Introduction to probability
9.1 Sample Space and Events
9.2 Events
9.3 Probabilities De ned on Events
9.4 Counting Rules, Combinations, and Permutations
9.5 Approaches Assigning Probabilities
9.6 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 191 / 463
Lecture - 9: Introduction to probability
Chapter 3: Introduction to
probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 192 / 463
Lecture - 9: Introduction to probability
Chance or Probability Theory
What is the chance of getting grade-A for the course MAT-211?
What are the chances that sales will decrease if we increase prices?
What is the likelihood a new assembly method will increase
productivity?
How likely is it that the project will be nished on time?
What is the chance that a new investment will be pro table?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 193 / 463
Lecture - 9: Introduction to probability Sample Space and Events
Sample Space and Events
Sample Space
an experiment is any action whose outcome is subject to uncertainty
(randomness) i.e., outcome is not predictable in advance
let us suppose that the set of all possible outcomes of an experiment
is known
the sample space of an experiment is the set of all possible outcomes
of the experiment and is denoted by S or Ω
Events
an event is a subset of the sample space
for example, S = {1, 3, 4} and A = {4, 1}, since A is a subset of the
sample space S and hence, A in an event
random experiment is the process of getting all possible events
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 194 / 463
Lecture - 9: Introduction to probability Sample Space and Events
Examples: Sample Space and Events
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 195 / 463
Lecture - 9: Introduction to probability Sample Space and Events
Other Examples: Sample Space
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 196 / 463
Lecture - 9: Introduction to probability Sample Space and Events
Practice Problem in the Classroom
1 What is the sample space when a coin is tossed three times?
2 What is the sample space for counting the number of females in a
group of n people?
3 A car repair is performed either on time or late and either satisfactorily
or unsatisfactorily. What is the sample space for a car repair?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 197 / 463
Lecture - 9: Introduction to probability Events
Events
Events
an event is a subset of the sample space
for example, S = {1, 3, 4} and A = {4, 1}, since A is a subset of the
sample space S and hence, A in an event
Complements of Events:
the complement of an event A, is the event consisting of everything in
the sample space S that is not contained within the event A
′
the notation A is used for the complement of A
for example, a six-sides dice has a sample space S = {1, 2, 3, 4, 5, 6}
if event A = {1, 3, 6} then complementary of event A = { 2, 4, 5}
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 198 / 463
Lecture - 9: Introduction to probability Probabilities De ned on Events
Probabilities De ned on Events
probability is a numerical measure of the likelihood that an event will
occur
the probability of an event is a number between 0 and 1, where,
roughly speaking, 0 indicates impossibility of the event and 1
indicates certainty
given a sample space S, probability, denoted by P, is a function that
satis es the following three conditions:
(i). 0 ≤ P(E ) ≤ 1,
(ii). P(S) = 1,
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 199 / 463
Lecture - 9: Introduction to probability Probabilities De ned on Events
Practice Problem in the Classroom
1 An experiment has ve outcomes, I, II, III, IV, and V. If P(I) = 0.13,
P(II) = 0.24, P(III) = 0.07, and P(IV) = 0.38, what is P(V)?
2 An experiment has ve outcomes, I, II, III, IV, and V. If P(I) = 0.08,
P(II) = 0.20, and P(III) = 0.33, what are the possible values for the
probability of outcome V? If outcomes IV and V are equally likely,
what are their probability values?
3 An experiment has three outcomes, I, II, and III. If outcome I is twice
as likely as outcome II, and outcome II is three times as likely as
outcome III, what are the probability values of the three outcomes?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 200 / 463
Lecture - 9: Introduction to probability Counting Rules, Combinations, and Permutations
If an experiment can be described as a sequence of k steps with n1
possible outcomes on the rst step, n2 possible outcomes on the
second step, and so on, then the total number of experimental
outcomes is given by (n1 )(n2 )⋯(nk )
Example: The experiment of tossing two coins can be thought of as a
two-step experiment in which step 1 is the tossing of the rst coin
and step 2 is the tossing of the second coin. If we use H to denote a
head and T to denote a tail, (H, H) indicates the experimental
outcome with a head on the rst coin and a head on the second coin.
The sample space is
S = {(H, H), (H, T ), (T , H), (T , T )}.
Viewing the experiment of tossing two coins as a sequence of rst
tossing one coin (n1 = 2) and then tossing the other coin (n2 = 2), we
can see from the counting rule that (2)(2) = 4 distinct experimental
outcomes are possible. The number of experimental outcomes in an
experiment involving tossing six coins is (2)(2)(2)(2)(2)(2) = 64.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 201 / 463
Lecture - 9: Introduction to probability Counting Rules, Combinations, and Permutations
Tree Diagram
A tree diagram is a graphical representation that helps in visualizing a
multiple-step experiment.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 202 / 463
Lecture - 9: Introduction to probability Counting Rules, Combinations, and Permutations
Counting rule for combination
A second useful counting rule allows one to count the number of
experimental outcomes when the experiment involves selecting n objects
from a (usually larger) set of N objects.
Consider a quality control procedure in which an inspector randomly
selects 2 of 5 parts to test for defects. In a group of ve parts, how many
combinations of two parts can be selected?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 203 / 463
Lecture - 9: Introduction to probability Counting Rules, Combinations, and Permutations
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 204 / 463
Lecture - 9: Introduction to probability Counting Rules, Combinations, and Permutations
Permutations
A third counting rule that is permutations. It allows one to compute the
number of experimental outcomes when n objects are to be selected from
a set of N objects where the order of selection is important.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 205 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Approaches Assigning Probabilities
there are three ways of assigning probability:
(i). classical,
(ii). empirical (Relative frequency method), and
(iii). subjective
the classical and empirical methods are objective and are based on
information and data
the subjective method is based on a person's belief or estimate of an
event's likelihood
it contains no formal calculations and only re ects the subject's
opinions and past experience
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 206 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Approaches Assigning Probabilities
Classical Probability
the classical probability is based on the assumption that the outcomes
of an experiment are equally likely
using the classical viewpoint, the probability of an event happening is
computed by dividing the number of favorable outcomes by the
number of possible outcomes:
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 207 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 208 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 209 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 210 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 211 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Complementary Event
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 212 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Example of Events
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 213 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Intersections of Events
contains common outcomes between two events
Suppose, A = {1, 3, 4} and B = {4}. What is the intersection of event
A and B?
A ∩ B = {4}
another example:
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 214 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Mutually Exclusive Events
events are mutually exclusive if the occurrence of any one event
means that none of the others can occur at the same time
two events A and B are said to be mutually exclusive if they have no
outcomes in common
for example, A = {1, 3, 4}, B = {5}, since event A and B don't have
any common outcome, so they are Mutually Exclusive Events
Unions of Events
consists of the outcomes that are contained within at least one of the
events A and B
for example, suppose A = {1, 3, 4}, B = {5}, then A ∪ B = {1, 3, 4, 5}
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 215 / 463
Lecture - 9: Introduction to probability Approaches Assigning Probabilities
Unions of Events
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 216 / 463
Lecture - 9: Introduction to probability Homework
Homework
Read the related topics of Chapter 4 of the text book
Exercise: 1-9, pp.158-159
Exercise: 14-21, pp.162-164
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 217 / 463
Lecture - 10: Basic rules for computing probability
Lecture - 10: Basic rules for computing probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 218 / 463
Lecture - 10: Basic rules for computing probability
10 Lecture - 10: Basic rules for computing probability
10.1 Joint and Marginal Probabilities
10.2 Conditional Probability
10.3 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 219 / 463
Lecture - 10: Basic rules for computing probability
Rule of addition for computing probabilities
▸ given a sample space S , probability, denoted by P or Pr, is a function
that satis es the following three conditions:
(i). 0 ≤ P(E ) ≤ 1,
(ii). Pr(S) = 1,
(iii). for mutually exclusive events E1 , E2 ∈ S
Pr(E1 ∪ E2 ) = Pr(E1 ) + Pr(E2 )
this is an addition rule for two mutually exclusive events
(iv). the addition rule for not mutually exclusive events is:
Pr(E1 ∪ E2 ) = Pr(E1 ) + Pr(E2 ) − Pr(E1 ∩ E2 )
▸ if two events are mutually exclusive, then the probability of both
occurring is denoted as P(E1 ∩ E2 ) and
P(E1 and E2 ) = P(E1 ∩ E2 ) = 0
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 220 / 463
Lecture - 10: Basic rules for computing probability
1 Example: A single 6-sided die is rolled. What is the probability of
rolling a 2 or a 5?
▸ Pr(2) = 16 and Pr(5) = 1
6
▸ therefore,
Pr(2 or 5) = Pr(2 ∪ 5) = Pr(2) + Pr(5)
1 1
= +
6 6
2
=
6
1
=
3
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 221 / 463
Lecture - 10: Basic rules for computing probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 222 / 463
Lecture - 10: Basic rules for computing probability
2 Example: In a Math class of 30 students, 17 are boys and 13 are girls.
On a unit test, 4 boys and 5 girls made an A grade. If a student is
chosen at random from the class, what is the probability of choosing
a girl or an A-grade student?
▸ Pr(girl) = 13
30 , Pr(A-grade student) =
9
30 and
5
Pr(girl ∩ A-grade student) = 30
▸ therefore,
Pr(girl or A-grade student) = Pr(girl) + Pr(A-grade student)
− Pr(girl ∩ A-grade student)
13 9 5
= + −
30 30 30
17
=
30
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 223 / 463
Lecture - 10: Basic rules for computing probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 224 / 463
Lecture - 10: Basic rules for computing probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 225 / 463
Lecture - 10: Basic rules for computing probability Joint and Marginal Probabilities
Joint and Marginal Probability
joint probability: the probability of two events both occurring; that
is, the probability of the intersection of two events
marginal probability: the values in the margins of a joint probability
table that provide the probabilities of each event separately
example:
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 226 / 463
Lecture - 10: Basic rules for computing probability Joint and Marginal Probabilities
Another Example
Find the joint and marginal probabilities table.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 227 / 463
Lecture - 10: Basic rules for computing probability Joint and Marginal Probabilities
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 228 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Independent Events and Conditional Probability
independent events
if two events, A and B are independent then the joint probability is
P(A and B) = P(A ∩ B) = P(A)P(B)
for example, if two coins are ipped, then the chance of both
being heads is
1 1 1
2×2=4
conditional probability
▸ is the probability of a particular event occurring, given that another
event has occurred, i. e., the conditional probability is
P(A ∩ B)
P(A∣B) =
P(B)
when events are independent then the occurrence of one event does
not aect the occurrence of another, then
Pr(A∣B) = Pr(A)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 229 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Continuous Assessment:
1 what the conditional probability when two events A and B are
mutually exclusive?
2 what the conditional probability that an event B is contained within
an event A, that is B ⊂A
Back to the Previous Example
what the conditional probability of event A occurring, given B?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 230 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Back to the Previous Example
(a). What is the probability that an o cer is promoted if he is a man?
(b). What is the probability that an o cer is promoted if she is a women?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 231 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Solution of (a).
Continuous Assessment:
(b). What is the probability that an o cer is promoted if she is a women?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 232 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Example: GAMES OF CHANC
Continuous Assessment:
(a). If somebody rolls a fair die without showing you but announces that
the result is even, then what is the probability of scoring a 6?
(b). What is the probability that at least one 6 is obtained on the two
dice?
(c). Suppose that somebody rolls the two dice without showing you but
announces that at least one 6 has been scored. What is the
probability that the red die scored a 6?
(d). If a red die and a blue die are thrown. What is the probability that
the red die scores a 6 given that an exactly one 6 has been score?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 233 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Solution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 234 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 235 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 236 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 237 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 238 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Example
Suppose that somebody secretly rolls two fair six-sided dice, and we
wish to compute the probability that the face-up value of the rst one
is 2, given the information that their sum is no greater than 5.
▸ Let D1 be the value rolled on die 1.
▸ Let D2 be the value rolled on die 2.
what is the probability that D1 = 2 given that D1 + D2 ≤ 5?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 239 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 240 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 241 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 242 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 243 / 463
Lecture - 10: Basic rules for computing probability Conditional Probability
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 244 / 463
Lecture - 10: Basic rules for computing probability Homework
Homework
Read the related topics of Chapter 4 of the text book
Course Guide, pp.34-36
Exercise: 22-27, pp.169-170
Exercise: 32-35, pp.176-177
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 245 / 463
Lecture - 11: Review Class
Lecture - 11: Review Class
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 246 / 463
Lecture - 11: Review Class
11 Lecture - 11: Review Class
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 247 / 463
Lecture - 12: Mid-term test
Lecture - 12: Mid-term test
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 248 / 463
Lecture - 12: Mid-term test
12 Lecture - 12: Mid-term test
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 249 / 463
Lecture - 12: Mid-term test
Chapter - 5 & 6: Discrete ad
Continuous Probability
Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 250 / 463
Lecture 13: Normal Distribution
Lecture 13: Normal Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 251 / 463
Lecture 13: Normal Distribution
13 Lecture 13: Normal Distribution
13.1 Random Variable
13.2 Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 252 / 463
Lecture 13: Normal Distribution Random Variable
Random Variable
a random variable is a numerical description of the outcome of a
random experiment
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 253 / 463
Lecture 13: Normal Distribution Random Variable
Concept of a Random Variable
consider a random experiment whose the sample space giving a
detailed description of each possible outcome when three electronic
components are tested may be written
Outcome NNN NDN NND DNN NDD DND DDN DDD
x 0 1 1 1 2 2 2 3
random variable
▸ is a variable (usually denoted by X , Y , Z , etc. and respectively it's
value is denoted by x , y , z , etc) whose value is determined by the
outcome of a random experiment
▸ is a function that associates a real number with each element in the
sample space
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 254 / 463
Lecture 13: Normal Distribution Random Variable
Example
Consider the sales of automobiles at DiCarlo Motors in Saratoga, New
York. Over the past 300 days of operation, sales data show 54 days
with no automobiles sold, 117 days with 1 automobile sold, 72 days
with 2 automobiles sold, 42 days with 3 automobiles sold, 12 days
with 4 automobiles sold, and 3 days with 5 automobiles sold. Suppose
we consider the experiment of selecting a day of operation at DiCarlo
Motors and de ne the random variable of interest as x= the number
of automobiles sold during a day.
From historical data, we know x is a discrete random variable that
can assume the values 0, 1, 2, 3, 4, or 5.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 255 / 463
Lecture 13: Normal Distribution Random Variable
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 256 / 463
Lecture 13: Normal Distribution Random Variable
Graphical presentation of Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 257 / 463
Lecture 13: Normal Distribution Random Variable
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 258 / 463
Lecture 13: Normal Distribution Random Variable
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 259 / 463
Lecture 13: Normal Distribution Random Variable
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 260 / 463
Lecture 13: Normal Distribution Random Variable
Expected Value of a Random Variable
The expected value, or mean, of a random variable is a measure of
the central location for the random variable
n
µ = E (X ) = ∑ xi f (x)
i= 1
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 261 / 463
Lecture 13: Normal Distribution Random Variable
Variance Value of a Random Variable
The variance of a random variable is a measure of the variation for
2
the random variable. It is denoted by σ and de ned by
n
σ 2 = E (X − µ)2 = ∑(xi − µ)2 f (x)
i= 1
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 262 / 463
Lecture 13: Normal Distribution Random Variable
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 263 / 463
Lecture 13: Normal Distribution Random Variable
Practice in Classroom
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 264 / 463
Lecture 13: Normal Distribution Normal Probability Distribution
the most important probability distribution for describing a
continuous random variable is the normal probability distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 265 / 463
Lecture 13: Normal Distribution Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 266 / 463
Lecture 13: Normal Distribution Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 267 / 463
Lecture 13: Normal Distribution Normal Probability Distribution
Characteristics of the normal distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 268 / 463
Lecture 13: Normal Distribution Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 269 / 463
Lecture 13: Normal Distribution Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 270 / 463
Lecture 14: Standard Normal Distribution
Lecture 14: Standard Normal Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 271 / 463
Lecture 14: Standard Normal Distribution
14 Lecture 14: Standard Normal Distribution
14.1 Standard Normal Probability Distribution
14.2 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 272 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Standard Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 273 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
We start by showing how to compute the probability that z is less than or
equal to 1.00; that is, P(z ≤ 1.00). This cumulative probability is the area
under the normal curve to the left of z ≤ 1.00 in the following graph.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 274 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 275 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 276 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 277 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 278 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 279 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 280 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 281 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 282 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 283 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Practice in Classroom
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 284 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Practice in Classroom
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 285 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Practice in Classroom
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 286 / 463
Lecture 14: Standard Normal Distribution Standard Normal Probability Distribution
Practice in Classroom
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 287 / 463
Lecture 14: Standard Normal Distribution Homework
Homework
Read the related topics of Chapters 5-6 of the text book
Course Guide, pp.38-40 Text
Exercise: 10-25, pp.248-250
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 288 / 463
Lecture 15: Class Test - 2
Lecture 15: Class Test - 2
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 289 / 463
Lecture 15: Class Test - 2
15 Lecture 15: Class Test - 2
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 290 / 463
Lecture 15: Class Test - 2
Chapter - 7: Sampling and
Sampling Distributions
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 291 / 463
Lecture 16: Random Sampling Methods
Lecture 16: Random Sampling Methods
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 292 / 463
Lecture 16: Random Sampling Methods
16 Lecture 16: Random Sampling Methods
16.1 Population & Sample
16.2 Census & Survey
16.3 Sampling Methods
16.4 Simple Random Sampling
16.5 How to draw a simple random sample?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 293 / 463
Lecture 16: Random Sampling Methods Population & Sample
Population and Sample (from the rst lecture)
Target Population (usually, we refer to it as a population in
statistics)
▸ is the aggregate of all possible values of a variable or all possible
objects whose characteristics are of interest in any particular research
Sample
▸ is a part of the target population
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 294 / 463
Lecture 16: Random Sampling Methods Census & Survey
Random Sample
▸ is a representative part of the target population which has been drawn
randomly
Census
▸ method to collect data on the entire population
▸ As per as 2022 census, Bangladesh have a population of 165,158,616
people, of which 81,712,824 are male, while 83,347,206 are female. As
many as 113,063,587 of them live in rural areas and 52,009,072 live in
Urban.
▸ Bangladesh Population Census: 1974, 1981, 1991, 2001, 2011, 2022
▸ advantages of a Census accurate and complete information
▸ according to the UN, the census is featured by the following aspects:
(i) Individual enumeration, (ii) Universality within a de ned territory,
(iii) Simultaneity and (iv) De ned periodicity.
Sample survey
▸ method for collecting data about the random sample
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 295 / 463
Lecture 16: Random Sampling Methods Census & Survey
Disadvantages of a Census
▸ huge cost and time consuming
▸ data may become out-of-date once it is collected
▸ sometimes, not possible to carry out census as items unidenti able
Ex: sh in the sea
Census vs. Survey
▸ a census gathers information from
▸ in a survey, however, only part of
every entity in a population
the total population is selected
▸ data is accurately representative of
▸ since surveys do not represent the
the whole population and detailed
entire population, they are not
data can be made available right
quite as accurate or reliable
down to small areas
▸ the advantages of a census include
▸ there is comparatively less data to
process
accuracy and detail
▸ they are also expensive and time
▸ there is comparatively less
expensive and less time consuming
consuming
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 296 / 463
Lecture 16: Random Sampling Methods Census & Survey
Sampling or Sampling method
▸ the act, process, or technique of selecting a representative part of a
population for the purpose of determining parameters or characteristics
of the whole population
▸ a small part selected as a sample for inspection or analysis
Advantages of Sampling
▸ saving of time
▸ reduced cost
▸ detailed study
▸ accuracy of result
▸ administrative convenience
▸ impossibility of the use of census method, etc.
Disadvantages/Limitations of Sampling
▸ chances of bias
▸ di culties in selecting truly a representative sample
▸ in adequate knowledge in the subject
▸ changeability of sampling units
▸ impossibility of sampling, etc.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 297 / 463
Lecture 16: Random Sampling Methods Census & Survey
Sampling Error
▸ the error, which arises entirely due to sampling and no other reasons
can be attributed to cause such error, is called sampling error
▸ is the dierence between a sample statistic and its corresponding
population parameter
Non-sampling Error
▸ non-sampling error can be attributed to sources other than sampling
and they may be random or non-random
Non-response Error
▸ non-response error arises when some of the respondent included in the
sample does not respond
Response Error
▸ response error arises when respondent give inaccurate answer or their
answers are misreported
Other Sampling Errors (i) sampling frame error (ii) data analysis error
(iii) respondent selection error (iv) questioning error (v) recoding
error, etc.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 298 / 463
Lecture 16: Random Sampling Methods Census & Survey
Sampling Units
▸ Sample units are the members of the population from which
measurements are taken during sampling
▸ examples
∎ all rickshaw puller of J.U campus
∎ all under ve children of J.U
∎ all sex worker of a brothel
Sampling Frame
▸ a sampling frame is a representation of the elements of the target
population
▸ it consist of a least or a set of narrations for identify the target
population
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 299 / 463
Lecture 16: Random Sampling Methods Census & Survey
Advantages of sampling over complete count
▸ saving of time ▸ accuracy of result
▸ reduced cost ▸ administrative convenience
▸ detailed study ▸ impossibility of the use of census
method
Sampling with and without replacement
▸ if the speci ed procedure of selection of the units permits the selected
unit at each draw to go back into the population and allows it to get
selected again it is called as sampling with replacement
▸ the selected unit at each draw is not permitted go back to the
population and is not allowed to get selected more than once, it is
termed as sampling without replacement in more cases
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 300 / 463
Lecture 16: Random Sampling Methods Sampling Methods
Sampling Methods
Sampling techniques may be broadly classi ed as
1 non-probability sampling
(i). convenience Sampling
(ii). judgement Sampling
(iii). quota Sampling
(iv). snowball Sampling or networking Sampling
2 probability sampling
(i). simple random sampling
(ii). strati ed random sampling
(iii). systematic random sampling
(iv). cluster sampling
∎ rst-stage cluster sampling
∎ second-stage cluster sampling
∎ multi-stage cluster sampling
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 301 / 463
Lecture 16: Random Sampling Methods Sampling Methods
Collection of Data
Sampling methods
1 simple random sampling
⇒ same/equal chance to select sampling unit
2 strati ed random sampling
⇒ selection of a sampling unit from each stratum
3 systematic random sampling
⇒ rst sampling unit is selected by randomly then every k th member
of the population is selected
4 cluster sampling
⇒ selection of all (or some) sampling unit from selected cluster(s)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 302 / 463
Lecture 16: Random Sampling Methods Sampling Methods
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 303 / 463
Lecture 16: Random Sampling Methods Sampling Methods
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 304 / 463
Lecture 16: Random Sampling Methods Sampling Methods
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 305 / 463
Lecture 16: Random Sampling Methods Simple Random Sampling
What is meant by Simple Random Sample?
a simple random sample is a subset of a statistical population in which
each member of the subset has an equal probability of being chosen.
it is the basic sampling technique where we select a group of subjects
(a sample) for study from a larger group (a population)
each individual is chosen entirely by chance and each member of the
population has an equal chance of being included in the sample
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 306 / 463
Lecture 16: Random Sampling Methods Simple Random Sampling
Advantages of Simple Random Sampling
. it is very simple the researcher need not exercise his brain in
deciding whether a particular unit can be representative or not
. simple random sample provides foundation for much of statistical
theory
. it is free from bias and therefore not aected by the choice of the
researcher
. it is generally more representative because each unit has equal chance
of being selected
. simple random sample provides a basis to which other methods can
be compared
. assessment of sampling error can be made and it is possible to
calculate the limit of error due to sampling
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 307 / 463
Lecture 16: Random Sampling Methods Simple Random Sampling
Disadvantages of Simple Random Sampling
SRS suers from the following disadvantages:-
. it is very di cult to have completely catalogued universe and thus
selection according to strictly random basis is frequently not possible
. cases studied may be too widely dispersed or even impossible to
contact and thus adherence in the whole sample may not be possible
. if units are of dierent sizes and the population consists of many
heterogeneous units simple random sampling method is unsuitable
. sampled individuals may be so widely dispersed that visiting each
selected individual may be extremely expensive and time consuming
. when the population measurements vary considerably in size, then
simple random sample produces larger variances than other methods
of sampling
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 308 / 463
Lecture 16: Random Sampling Methods Simple Random Sampling
Simple Random Sample vs. Random Sample
. the dierence between the two is that with a simple random sample,
each object in the population has an equal chance of being chosen
whereas with random sampling, each object does not necessarily have
an equal chance of being chosen
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 309 / 463
Lecture 16: Random Sampling Methods How to draw a simple random sample?
How to draw a sample by simple random sampling?
lottery method
table of random numbers
computer random number generator
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 310 / 463
Lecture 16: Random Sampling Methods How to draw a simple random sample?
Steps for obtaining a simple random sample
Step 1: de ne a target population
Step 2: make a sampling frame and assign a sequential number 1, 2,
3,... for the sampling frame
Step 3: gure out what your sample size (n) is going to be
Step 4: use a random number generator to select the sample, using
your sampling frame (population size) from target population
(i). select at random, any page of the random number table and pick up
the numbers in any row, column or diagonal at random
(ii). the population units corresponding to the numbers in step (i)
constitute the random samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 311 / 463
Lecture 16: Random Sampling Methods How to draw a simple random sample?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 312 / 463
Lecture 16: Random Sampling Methods How to draw a simple random sample?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 313 / 463
Lecture 16: Random Sampling Methods How to draw a simple random sample?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 314 / 463
Lecture 16: Random Sampling Methods How to draw a simple random sample?
Then, in the given random number table, starting with the rst
number and moving row wise (or column wise or diagonal wise) to
pick out the numbers in pairs, one by one, ignoring those numbers
which are greater than 50, until a selection of 10 numbers is made.
Selected row-wise sample numbers: 27, 15, 45, 11, 02, 14, 18, 07, 39,
31
Selected row-wise monthly pocket money (TK/-) of 10 students out
of 50: 7100, 2400, 3700, 7500, 1500, 2000, 6500, 3000, 1700, 7600.
bf Homework: Calculate mean and standard deviation of 10 students'
monthly pocket money (Use formula and scienti c calculator)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 315 / 463
Lecture 16: Random Sampling Methods How to draw a simple random sample?
Homework
HW: Read Chapter 7 of the text book
Exercises: 3-8, pp.272-273
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 316 / 463
Lecture 16: Random Sampling Methods How to draw a simple random sample?
Chapter - 8: Interval estimation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 317 / 463
Lecture 17: Interval estimation
Lecture 17: Interval estimation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 318 / 463
Lecture 17: Interval estimation
17 Lecture 17: Interval estimation
17.1 Interval Estimation
17.2 Con dence interval for µ based on large samples
17.3 Con dence interval for µ based on small samples
17.4 Con dence interval for variance and standard deviation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 319 / 463
Lecture 17: Interval estimation Interval Estimation
Estimation
There are two types of estimation
Point estimation
It is the single best value. For example, mean and SD of total marks
for a course of IUB students are point estimates because these are
single value
Interval estimation
Interval estimation is the use of sample data to calculate an interval
of possible (or probable) values of an unknown population parameter,
in contrast to point estimation, which is a single number.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 320 / 463
Lecture 17: Interval estimation Interval Estimation
What is meant by the con dence interval?
A con dence interval is an interval estimate with a speci c level of
con dence. A level of con dence is the probability that the interval
estimate will contain the parameter. The level of con dence is 1 − α. 1 − α
area lies within the con dence interval.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 321 / 463
Lecture 17: Interval estimation Con dence interval for µ based on large samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 322 / 463
Lecture 17: Interval estimation Con dence interval for µ based on large samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 323 / 463
Lecture 17: Interval estimation Con dence interval for µ based on large samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 324 / 463
Lecture 17: Interval estimation Con dence interval for µ based on large samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 325 / 463
Lecture 17: Interval estimation Con dence interval for µ based on large samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 326 / 463
Lecture 17: Interval estimation Con dence interval for µ based on large samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 327 / 463
Lecture 17: Interval estimation Con dence interval for µ based on large samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 328 / 463
Lecture 17: Interval estimation Con dence interval for µ based on large samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 329 / 463
Lecture 17: Interval estimation Con dence interval for µ based on small samples
Con dence interval for µ based on small samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 330 / 463
Lecture 17: Interval estimation Con dence interval for µ based on small samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 331 / 463
Lecture 17: Interval estimation Con dence interval for µ based on small samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 332 / 463
Lecture 17: Interval estimation Con dence interval for µ based on small samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 333 / 463
Lecture 17: Interval estimation Con dence interval for µ based on small samples
Con dence interval for µ based on small sample size
When sample size is less than 30, i.e., n < 30, the sampling distribution of
the sample is a student's-t distribution. The student's-t distribution is
very similar to the standard normal distribution.
it is symmetric about its mean
as the sample size increases, the t -distribution approaches the normal
distribution
it is a bell shaped distribution.
(1 − α)100% Con dence interval for µ
s s
x̄ − t α ,(n−1) √ ≤ µ ≤ x̄ + t α ,(n−1) √
2 n 2 n
this formula is used when n < 30 and population standard deviation σ is
unknown.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 334 / 463
Lecture 17: Interval estimation Con dence interval for µ based on small samples
Problem 1
Suppose we have given sample heights of 20 IUB students, where
x̄ = 67.3” and standard deviation is 3.6”, and the distribution is symmetric.
Develop a 95% con dence interval for the population mean and make a
summary based on your ndings.
Solution:
Let X is height of the students. It is given that X ∼ N(µ, 3.6”) and n = 20.
95% Con dence interval for µ
s s
x̄ − t α ,(n−1) √ ≤ µ ≤ x̄ + t α ,(n−1) √
2 n 2 n
Here, x̄ = 67.3”, s = 3.6”, n = 25, α = 1 − 0.95 = 0.05, α/2 = 0.025 and
t α
n
,(n− 1) = t0.025,(19) = 2.093. Thus
3.6 3.6
67.3 − 2.093 × √ ≤ µ ≤ 67.3 + 2.093 × √ ⇒ 65.61 ≤ µ ≤ 68.98
20 20
Summary: Based on our ndings, we are 95% con dent that population
mean is ranging 65.61 to 68.98.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 335 / 463
Lecture 17: Interval estimation Con dence interval for µ based on small samples
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 336 / 463
Lecture 17: Interval estimation Con dence interval for µ based on small samples
Home Work
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 337 / 463
Lecture 17: Interval estimation Con dence interval for variance and standard deviation
Con dence Interval for σ 2
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 338 / 463
Lecture 17: Interval estimation Con dence interval for variance and standard deviation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 339 / 463
Lecture 17: Interval estimation Con dence interval for variance and standard deviation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 340 / 463
Lecture 17: Interval estimation Con dence interval for variance and standard deviation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 341 / 463
Lecture 17: Interval estimation Con dence interval for variance and standard deviation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 342 / 463
Lecture 17: Interval estimation Con dence interval for variance and standard deviation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 343 / 463
Lecture 17: Interval estimation Con dence interval for variance and standard deviation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 344 / 463
Lecture 17: Interval estimation Con dence interval for variance and standard deviation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 345 / 463
Lecture 17: Interval estimation Con dence interval for variance and standard deviation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 346 / 463
Lecture 18: Interval Estimations about Two Population Means
Lecture 18: Interval Estimations about Two Population
Means
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 347 / 463
Lecture 18: Interval Estimations about Two Population Means
18 Lecture 18: Interval Estimations about Two Population Means
18.1 Interval Estimation of µ1 − µ2
18.2 Determining the Sample Size
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 348 / 463
Lecture 18: Interval Estimations about Two Population Means Interval Estimation of µ1 − µ2
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 349 / 463
Lecture 18: Interval Estimations about Two Population Means Interval Estimation of µ1 − µ2
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 350 / 463
Lecture 18: Interval Estimations about Two Population Means Interval Estimation of µ1 − µ2
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 351 / 463
Lecture 18: Interval Estimations about Two Population Means Interval Estimation of µ1 − µ2
Exercises
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 352 / 463
Lecture 18: Interval Estimations about Two Population Means Interval Estimation of µ1 − µ2
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 353 / 463
Lecture 18: Interval Estimations about Two Population Means Interval Estimation of µ1 − µ2
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 354 / 463
Lecture 18: Interval Estimations about Two Population Means Determining the Sample Size
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 355 / 463
Lecture 18: Interval Estimations about Two Population Means Determining the Sample Size
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 356 / 463
Lecture 18: Interval Estimations about Two Population Means Determining the Sample Size
Chapter - 9: Hypothesis Tests
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 357 / 463
Lectures 19: Tests of hypothesis
Lectures 19: Tests of hypothesis
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 358 / 463
Lectures 19: Tests of hypothesis
19 Lectures 19: Tests of hypothesis
19.1 Problems & Motivation
19.2 The Null and Alternative Hypotheses
19.3 Key Components of Test of Hypothesis
19.4 The p -value
19.5 Basic Steps for Test of Hypothesis
19.6 Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 359 / 463
Lectures 19: Tests of hypothesis
Tests of hypothesis
In general, we do not know the true value of population parameters
(mean, proportion, variance, SD and others). They must be
estimated based on random samples. However, we do have
hypotheses about what the true values are.
The major purpose of hypothesis testing is to choose between two
competing hypotheses about the value of a population parameter
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 360 / 463
Lectures 19: Tests of hypothesis Problems & Motivation
Problems & Motivation
1 from long-term experience, a factory owner knows that a worker can
produce a product in an average time of 89 min. however, on Sunday
morning, there is the impression that it takes longer. how do you
justify whether this impression is correct or not?
2 is there any association between smoking habit and Myocardial
Infarction (MI)?
Myocardial Infarction
Smoking Heart attack No heart attack total
Smoker 325 175 500
Non-smoker 175 325 500
total 500 500 1000
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 361 / 463
Lectures 19: Tests of hypothesis Problems & Motivation
Problems & Motivation
3 eect of coee drinking on cancer
the scientist want to see the
disease and they may assume that coee drinking increases the risk of
cancer in humans
how do we justify these hypotheses?
a hypothesis is an assertion or assumption concerning about the
population parameter or characteristics of random variables
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 362 / 463
Lectures 19: Tests of hypothesis The Null and Alternative Hypotheses
(1). Statistical Hypothesis
Hypothesis
Null Hypothesis Alternatively Hypothesis
(denoted by H0 ) (denoted by H1 or Ha )
▸ assumed to be true ▸ any statement without H0
▸ a given value ▸ rejection of true value, a
given
▸ assumption, nothing new
▸ independent
▸ rejection of the assumption
▸ negation of the research aim
▸ does not contain equality
(usually contains >, <, ≠)
▸ usually contains an equality (e.g, =,
≥, ≤)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 363 / 463
Lectures 19: Tests of hypothesis The Null and Alternative Hypotheses
Exercise
1 The manager of an automobile dealership is considering a new bonus
plan designed to increase sales volume. Currently, the mean sales
volume is 14 automobiles per month. The manager wants to conduct
a research study to see whether the new bonus plan increases sales
volume. To collect data on the plan, a sample of sales personnel will
be allowed to sell under the new bonus plan for a 1-month period.
De ne the null and the alternative hypotheses.
2 The manager of an automobile dealership is considering a new bonus
plan designed to increase sales volume. Currently, the mean sales
volume is 14 automobiles per month. The manager wants to conduct
a research study to see whether the new bonus plan decreases sales
volume. To collect data on the plan, a sample of sales personnel will
be allowed to sell under the new bonus plan for a 1-month period.
De ne the null and the alternative hypotheses.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 364 / 463
Lectures 19: Tests of hypothesis The Null and Alternative Hypotheses
Exercise
3 The manager of an automobile dealership is considering a new bonus
plan designed to increase sales volume. Currently, the mean sales
volume is 14 automobiles per month. The manager wants to conduct
a research study to see whether the new bonus plan changes sales
volume. To collect data on the plan, a sample of sales personnel will
be allowed to sell under the new bonus plan for a 1-month period.
De ne the null and the alternative hypotheses.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 365 / 463
Lectures 19: Tests of hypothesis The Null and Alternative Hypotheses
Exercise
4 The manager of the Danvers-Hilton Resort Hotel stated that the
mean guest bill for a weekend is $600 or less. A member of the
hotel's accounting sta noticed that the total charges for guest bills
have been increasing in recent months. The accountant will use a
sample of weekend guest bills to test the manager's claim.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 366 / 463
Lectures 19: Tests of hypothesis Key Components of Test of Hypothesis
Key Components of Test of Hypothesis
(2). Level of signi cance
types of error
reject H0 when it is true do not reject H0 when it false
(type I error) (type II error)
In Reality
H0 is TRUE H0 is FALSE
Correct Decision Type II error
Decision
Accept H0 1 − α = Con dence level β = Pr(Type II Error)
Type I Error Correct Decision
Reject H0 α = Pr(Type I Error) 1 − β =Power of the test
▸ α is also called the level of signi cance and x it rst
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 367 / 463
Lectures 19: Tests of hypothesis Key Components of Test of Hypothesis
(3). Test statistic
▸ is a random variable that is calculated from sample data and used in a
hypothesis test
▸ in general, the test statistic for the null hypothesis H0 ∶ θ = θ0 is
θ̂ − θ0
test statistic =
̂
se(θ)
▸ Z -test statistic
▸ t -test statistic
▸ F -test statistic
▸ χ2 -test statistic
▸ ⋯
(4). Critical region: is the region of values that corresponds to the
rejection of the null hypothesis at some chosen probability level
▸ acceptance region
▸ rejection region
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 368 / 463
Lectures 19: Tests of hypothesis Key Components of Test of Hypothesis
Acceptance / Rejection regions (One-sided Ha )
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 369 / 463
Lectures 19: Tests of hypothesis Key Components of Test of Hypothesis
Acceptance / Rejection regions (Two-sided Ha )
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 370 / 463
Lectures 19: Tests of hypothesis Key Components of Test of Hypothesis
(5). Decision rule
▸ reject H0
∎ if the value of test statistic belongs to the rejection region at level of
signi cance 100α%
∎ or p -value is less then α
▸ otherwise, do not reject H0 at level of signi cance 100α%
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 371 / 463
Lectures 19: Tests of hypothesis The p -value
The p -value
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 372 / 463
Lectures 19: Tests of hypothesis Basic Steps for Test of Hypothesis
Basic Steps for Test of Hypothesis
. Step 1: State the null and alternative Hypothesis
. Step 2: Set level of signi cance, usually, denoted by α
. Step 3: Collect Data and de ne a test statistic and then compute it
. Step 4: Construct Acceptance / Rejection regions by collecting
tabulated value from
▸ standard normal table for Z -test
▸ standard t -table for t -test
▸ F -table for F -test
▸ χ2 -table for χ2 -test
for the level of signi cance α or compute p−value and then de ne
decision rule
. Step 5: Based on steps 3 and 4, draw a conclusion about H0
▸ reject H0
∎ if the value of test statistic belongs to the rejection region at level of
signi cance 100α%
∎ or p -value is less then α
▸ otherwise, do not reject H0 at level of signi cance 100α%
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 373 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Example: Normal distribution with known σ 2
Example: From long-term experience, a factory owner knows that a
worker can produce a product in an average time of 89 min. However,
on Sunday morning, there is the impression that it takes longer. How
do you justify whether this impression is correct or not?
to test whether this impression is correct, a sample (n = 12) is taken
with x̄ = 92.2
we assume that the production time is normal with σ 2 = 144
Step 1: we get that the hypothesis
H0 ∶ µ = 89
vs. Ha ∶ µ > 89
we generalize this situation and consider the following one-side test
⎧
⎪
⎪ H0 ∶ µ = µ0
⎨
⎪ µ > µ0
⎩ Ha ∶
⎪
Step 2: select the level of signi cance level α = 5% , i.e., α = 0.05
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 374 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Step 3: test statistic
we have that n = 12, x̄ = 92.2 and σ 2 = 144 such that
92.2 − 89
zcal = √ = 0.9237
12/ 12
Step 4: critical value
x̄ − µ0
zcal = √ ∼ N ( 0, 1) under H0
σ/ n
we use the signi cance level α to nd the critical value a
from the table of the standard normal we get that a = zα
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 375 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 376 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
in the example, we reject H0 if the test statistic is within the interval
[zα , +∞) = [1.645, +∞)
Step 5: decision
since,
zcal = 0.9237 < 1.645
we can not reject H0 at signi cance level 5%
there is insu cient evidence to show that it takes longer to produce
on Sunday morning
Alternatively
we nd the same conclusion from the p -value
p -value = Pr(Z > 0.9237) = 0.1778
since p -value is larger than 0.05, then we do not reject H0 at
signi cance level 5%
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 377 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Exercise
Benzene is a possible cancer-agent. We want to look whether in a chemical
company the concentration of Benzene in the air is greater than 1 ppm.
0.21 1.44 2.54 2.97 0.00
3.91 2.24 2.41 4.50 0.15
0.30 0.36 4.50 5.03 0.00
2.89 4.71 0.85 2.60 1.26
As hypotheses, we get
⎧
⎪
⎪ H0 ∶ µ=1
⎨
⎪
⎩ Ha ∶
⎪ µ>1
Test this hypothesis by using 5% level of signi cance.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 378 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Exam Question-1
Individuals ling federal income tax returns prior to March 31 had an
average refund of $1056. Consider the population of last minute lers who
mail their returns during the last 5 days of the income tax period typically
April 10 to April 15. A researcher suggests that one of the reasons
individuals wait until the last 5 days to le their returns is that on average
those individuals have a lower refund than early llers.
(a). Develop appropriate hypotheses such that rejection of null hypothesis
will support the researcher's argument.
(b). Using 5% level of signi cance, what is the critical value for the test
statistic and what is the rejection rule?
(c). For a sample of 400 individuals who led a return between April 10
and April 15, the sample mean refund was $910 and the sample
standard deviation was $1600. Compute the value of the test statistic.
(d). What is your conclusion?
(e). What is the p -value for the test?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 379 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 380 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 381 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Exam Question-2
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 382 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 383 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 384 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Exam Question-3
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 385 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 386 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 387 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 388 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Exam Question-4
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 389 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 390 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 391 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 392 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 393 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 394 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 395 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 396 / 463
Lectures 19: Tests of hypothesis Testing on a Single Mean
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 397 / 463
Lectures 20: Tests of hypothesis (Conti...)
Lectures 20: Tests of hypothesis (Conti...)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 398 / 463
Lectures 20: Tests of hypothesis (Conti...)
20 Lectures 20: Tests of hypothesis (Conti...)
20.1 Testing on a Single Proportion
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 399 / 463
Lectures 20: Tests of hypothesis (Conti...)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 400 / 463
Lectures 20: Tests of hypothesis (Conti...)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 401 / 463
Lectures 20: Tests of hypothesis (Conti...)
The One-Sample Problem: Mean Test
rst we develop some hypothesis test for the mean µ of a population X
and we distinguish the following three cases
1 X has a normal distribution, i.e., X ∼ N (µ, σ 2 ) with
▸ 2
known variance σ
▸ unknown variance σ 2
2 X has a general distribution, but we have a large sample size (n ≥ 30)
Hypothesis H0 ∶ µ = µ0 vs. H1 ∶ µ ≠ µ0
Assumption σ 2 is known σ 2 is unknown
any n n < 30 n ≥ 30
Test statistic zcal = (x̄−µ0 )
√
σ/ n
tcal = (x̄−µ0 )
σ
√
̂/ n
zcal = (x̄−µ0 )
σ
√
̂/ n
if ∣zcal ∣ > z α2 if ∣tcal ∣ > t α2 if ∣zcal ∣ > z α2
Reject H0 p -value< α p -value< α p -value< α
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 402 / 463
Lectures 20: Tests of hypothesis (Conti...)
One Sided Mean Test
Hypothesis H0 ∶ µ = µ0 vs. H1 ∶ µ > µ0 or H1 ∶ µ < µ0
Assumption σ 2 is known σ 2 is unknown
any n n < 30 n ≥ 30
Test statistic zcal = (x̄−µ0 )
√
σ/ n
tcal = (x̄−µ0 )
σ
√
̂/ n
zcal = (x̄−µ0 )
σ
√
̂/ n
if ∣zcal ∣ > zα if ∣tcal ∣ > tα if ∣zcal ∣ > z α2
Reject H0 p -value< α p -value< α p -value< α
p -value = Pr(T ≥ tcal ∣H0 ) for right sided Ha ,
p -value = Pr(T ≤ tcal ∣H0 ) for left sided Ha ,
p -value = 2 min{Pr(T ≤ tcal ∣H0 ), Pr(T ≥ tcal ∣H0 )} for both sided Ha
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 403 / 463
Lectures 20: Tests of hypothesis (Conti...) Testing on a Single Proportion
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 404 / 463
Lectures 20: Tests of hypothesis (Conti...) Testing on a Single Proportion
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 405 / 463
Lectures 20: Tests of hypothesis (Conti...) Testing on a Single Proportion
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 406 / 463
Lectures 20: Tests of hypothesis (Conti...) Testing on a Single Proportion
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 407 / 463
Lectures 20: Tests of hypothesis (Conti...) Testing on a Single Proportion
Chapter - 10: Correlation Analysis
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 408 / 463
Lecture 21: Correlation Analysis
Lecture 21: Correlation Analysis
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 409 / 463
Lecture 21: Correlation Analysis
21 Lecture 21: Correlation Analysis
21.1 Scatter Diagram
21.2 Covariance
21.3 Correlation Coe cient
21.4 Exercises
21.5 Test for Signi cance Using Correlation
21.6 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 410 / 463
Lecture 21: Correlation Analysis Scatter Diagram
Scatter Diagram
a scatter diagram is a graphic tool used to display the relationship between
two variables
the dependent variable is scaled on the Y-axis and is the variable
being estimated
the independent variable is scaled on the X-axis and is the variable
used as the predictor
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 411 / 463
Lecture 21: Correlation Analysis Covariance
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 412 / 463
Lecture 21: Correlation Analysis Covariance
Sample Covariance
what is the nature of the relationship between x and y?
sample covariance:
∑(xi − x̄)(yi − xy
¯)
sxy =
n−1
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 413 / 463
Lecture 21: Correlation Analysis Covariance
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 414 / 463
Lecture 21: Correlation Analysis Correlation Coe cient
What is Correlation Analysis?
Correlation analysis
▸▸ a group of techniques to measure the relationship between two variables
Pearson's Correlation coe cient
is a measure of the strength of the linear relationship between two
variables
is denoted by r or rxy and de ned as
n
∑ (xi − x̄)(yi − ȳ )
i=1
rxy =√ √
n n
∑ (xi − x̄)2 ∑ (yi − ȳ )2
i=1 i=1
n
1
where x̄ = n ∑ xi (the sample mean); and analogously for ȳ
i=1
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 415 / 463
Lecture 21: Correlation Analysis Correlation Coe cient
Pearson's Correlation Coe cient
this correlation coe cient is called the Pearson's correlation coe cient
whicgh is also de ned as
n
∑ xi yi − nx̄ ȳ
i=1
rxy =¿ ¿
Á n Á n
À( ∑ x 2 − nx̄ 2 ) Á
Á À( ∑ y 2 − nȳ 2 )
i= 1 i
i= 1 i
sxy
=
sx sy
√
sx = 1 ∑ n
2
where
n−1 i=1(xi − x̄) (the sample standard deviation); and
analogously for sy
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 416 / 463
Lecture 21: Correlation Analysis Correlation Coe cient
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 417 / 463
Lecture 21: Correlation Analysis Correlation Coe cient
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 418 / 463
Lecture 21: Correlation Analysis Correlation Coe cient
Correlation Coe cient
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 419 / 463
Lecture 21: Correlation Analysis Correlation Coe cient
Correlation Coe cient
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 420 / 463
Lecture 21: Correlation Analysis Correlation Coe cient
How do you interpret the value of correlation coe cient?
the following drawing summarizes the strength and direction of the
correlation coe cient
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 421 / 463
Lecture 21: Correlation Analysis Correlation Coe cient
Write down the properties (or characteristics) of the
correlation coe cient.
Characteristics of correlation coe cient
1 the sample correlation coe cient is identi ed by the lowercase letter r
2 it shows the direction and strength of the linear relationship between
two interval or ratio-scale variables
3 it ranges from −1 up to and including +1
4 a value near 0 indicates there is little linear relationship between the
variables
5 a value near 1 indicates a direct or positive linear relationship between
the variables
6 a value near −1 indicates an inverse or negative linear relationship
between the variables
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 422 / 463
Lecture 21: Correlation Analysis Exercises
Exercises
1 The following sample of observations were randomly selected.
x 4 5 3 6 10
y 4 6 5 7 7
(a). Draw a scatter diagram.
(b). Determine the correlation coe cient and interpret the relationship between x
and y .
(c). Interpret these statistical measures.
Solution (b)
x y x2 y2 xy
4 4 16 16 16
5 6 25 36 30
3 5 9 25 15
6 7 36 49 42
10 7 100 49 70
∑ xi = 28 ∑ yi = 29 ∑ xi2 = 186 ∑ yi2 = 175 ∑ xi yi = 173
x̄ = 5.6 ȳ = 5.8
n
∑ xi yi − nx̄ ȳ
rxy =¿
1 i=
¿ =√
173 × −5 × 5.6 × 5.8
√ = 0.7522
Á n Á n 186 − 5 × (5.6)2 175 − 5 × (5.8)2
À( ∑ x 2 − nx̄ 2 ) Á
Á À( ∑ y 2 − nȳ 2 )
i=1 i
i= 1 i
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 423 / 463
Lecture 21: Correlation Analysis Exercises
Exercises
2 The owner of Maumee Ford-Volvo wants to study the relationship
between the age of a car and its selling price. Listed below is a
random sample of 12 used cars sold at the dealership during the last
year.
Car Age (years) Selling Price ($000) Car Age (years) Selling Price ($000)
1 9 8.1 7 8 7.6
2 7 6.0 8 11 8.0
3 11 3.6 9 10 8.0
4 12 4.0 10 12 6.0
5 8 5.0 11 6 8.6
6 7 10.0 12 6 8.0
(a). Draw a scatter diagram.
(b). Determine the correlation coe cient.
(c). Interpret the correlation coe cient. Does it surprise you that the
correlation coe cient is negative?
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 424 / 463
Lecture 21: Correlation Analysis Test for Signi cance Using Correlation
Test whether the linear relationship is signi cant or not.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 425 / 463
Lecture 21: Correlation Analysis Test for Signi cance Using Correlation
Another Example
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 426 / 463
Lecture 21: Correlation Analysis Test for Signi cance Using Correlation
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 427 / 463
Lecture 21: Correlation Analysis Test for Signi cance Using Correlation
Example
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 428 / 463
Lecture 21: Correlation Analysis Test for Signi cance Using Correlation
Conclusion: Since the calculated value of t = 3.297 belongs to the
rejection region, we reject H0 . It means that there is a signi cant linear
relationship between calls (Y ) and sales (X ).
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 429 / 463
Lecture 21: Correlation Analysis Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 430 / 463
Lecture 21: Correlation Analysis Homework
Homework
HW: Read the Section 3.5 in Chapter 3 of the text book
Exercises: 45-51, Pages 122-123
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 430 / 463
Lecture 21: Correlation Analysis Homework
Chapter - 11: Regression Analysis
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 431 / 463
Lecture 22: Regression Analysis
Lecture 22: Regression Analysis
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 432 / 463
Lecture 22: Regression Analysis
22 Lecture 22: Regression Analysis
22.1 Concept of Regression Analysis
22.2 Linear Regression Model
22.3 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 433 / 463
Lecture 22: Regression Analysis Concept of Regression Analysis
Regression Analysis
an equation that expresses the relationship between two variables
in regression analysis, we nd the relationship among variables and we
also estimate or predict one variable based on another variable
regression analysisdescribes how a set of independent variables is
numerically related to the dependent variable
the variable being predicted or estimated is called the is the
dependent variable
the variable or variables being used to predict the value of the
dependent variable are called the independent variables
both the independent and the dependent variables must be interval or
ratio scale
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 434 / 463
Lecture 22: Regression Analysis Concept of Regression Analysis
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 435 / 463
Lecture 22: Regression Analysis Linear Regression Model
Simple Linear Regression Model
suppose the linear mean regression model is
yi = β0 + β1 xi + εi ; i = 1, 2, . . . , n
where β0 is the constant or intercept and β1 is the slope coe cient
the β0 and β1 are also called regression coe cients
usually, β0 and β1 are unknown
we can estimate β0 and β1 by following methods
▸ ordinary least square (OLS) method
▸ maximum likelihood estimation
▸ method-of-moments
▸ ...
the estimated mean regression model (or equation) is
ŷi = b0 + b1 xi
where b0 and b1 are respectively, the estimator of β0 and β1
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 436 / 463
Lecture 22: Regression Analysis Linear Regression Model
where, the estimator of β0 and β1 are
b0 = ȳ − b1 x̄
n
∑ xi yi − nx̄ ȳ
b1 =
i= 1
∑ xi2 − nx̄ 2
n
i= 1
these estimators are also called ordinary least square (OLS) estimators
the expression of b1 can also be written as
n
∑ (xi − x̄)(yi − ȳ )
b1 =
i= 1
∑ (xi − x̄)2
n
i= 1
because
n n n n
2 2
∑(xi − x̄) = ∑ xi − nx̄
2 and ∑(xi − x̄)(yi − ȳ ) = ∑ xi yi − nx̄ ȳ
i= 1 i= 1 i= 1 i= 1
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 437 / 463
Lecture 22: Regression Analysis Linear Regression Model
Interpretation of Slope Coe cient
b1 is the slope of the tted (estimated) line
it shows the amount of change in ŷ for a change of one unit in x
a positive value for b1 indicates a direct relationship between the two
variables and a negative value indicates an inverse relationship
the sign of b1 and the sign of r, the correlation coe cient, are always
the same
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 438 / 463
Lecture 22: Regression Analysis Linear Regression Model
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 439 / 463
Lecture 22: Regression Analysis Linear Regression Model
Example
To illustrate the least squares method, suppose data were collected from a
sample of 10 Armand's Pizza Parlor restaurants located near college
campuses. For the i th observation or restaurant in the sample, xi is the
size of the student population (in thousands) and yi is the quarterly sales
(in thousands of dollars).
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 440 / 463
Lecture 22: Regression Analysis Linear Regression Model
(i). Show the relationship between the size of student population and the
quarterly sales by using scatter diagram. Make a comment on the
scatter diagram.
(ii). Write down the regression model and estimated regression equation.
(ii). Find the least square estimates and write the estimated regression
equation. Interpret the results.
(iv). Draw the regression line.
(v). Predict quarterly sales for a restaurant to be located near a campus
with 16,000 students.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 441 / 463
Lecture 22: Regression Analysis Linear Regression Model
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 442 / 463
Lecture 22: Regression Analysis Linear Regression Model
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 443 / 463
Lecture 22: Regression Analysis Linear Regression Model
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 444 / 463
Lecture 22: Regression Analysis Linear Regression Model
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 445 / 463
Lecture 22: Regression Analysis Linear Regression Model
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 446 / 463
Lecture 22: Regression Analysis Linear Regression Model
To predict quarterly sales for a restaurant to be located near a campus
with 16,000 students, we would compute
ŷ = 60 + 5 × 16 = 140
Hence, we would predict quarterly sales of $140,000 for this restaurant.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 447 / 463
Lecture 22: Regression Analysis Linear Regression Model
Classroom Practice
1 The following sample of observations were randomly selected.
x 4 5 3 6 10
y 4 6 5 7 7
(a). Determine the regression equation.
(b). Write the estimated regression equation (or line).
(c). Determine the estimated value of y when x is 7.
Solution of the Exercises
x y x2 y2 xy
4 4 16 16 16
5 6 25 36 30
3 5 9 25 15
6 7 36 49 42
10 7 100 49 70
∑ xi = 28 ∑ yi = 29 ∑ xi2 = 186 ∑ yi2 = 175 ∑ xi yi = 173
x̄ = 5.6 ȳ = 5.8
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 448 / 463
Lecture 22: Regression Analysis Linear Regression Model
Solution of the Exercises
(a). the least square estimator of β0 and β1 are
n
∑ xi yi − nx̄ ȳ
b1 =
i= 1 = 0.3630 and b0 = ȳ − b1 x̄ = 3.7671
∑ xi2 − nx̄ 2
n
i=1
(b). hence the estimated equation (or line) is
ŷ = b0 + b1 x = 3.7671 + 0.3630x
(c). the estimated value of y is
ŷ = 3.7671 + 0.3630 × 7 = 6.3082
when x is 7.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 449 / 463
Lecture 22: Regression Analysis Linear Regression Model
Classroom Practice
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 450 / 463
Lecture 22: Regression Analysis Linear Regression Model
Classroom Practice (Hints.)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 451 / 463
Lecture 22: Regression Analysis Homework
Homework
HW: Read the Chapter 14 of the text book
Exercises: 01-09, 13, 14, Pages 570-575
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 452 / 463
Lecture 23: Regression Analysis (Conti...)
Lecture 23: Regression Analysis (Conti...)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 453 / 463
Lecture 23: Regression Analysis (Conti...)
23 Lecture 23: Regression Analysis (Conti...)
23.1 Coe cient of Determination (R )
2
23.2 Adjusted R2
23.3 Homework
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 454 / 463
Lecture 23: Regression Analysis (Conti...) Coe cient of Determination (R 2 )
Coe cient of Determination
the total sum of squares (proportional to the variance of the data):
SStot = ∑(yi − ȳ )2 ,
i
The sum of squares of residuals, also called the residual sum of
squares: SSres = ∑(yi − ŷi )2 = ∑ ε2i
i i
the coe cient of determination is the proportion of the total variation
in the dependent variable Y that is explained, or accounted for, by
the variation in the independent variable X
2
it is denoted by R and de ned by
R2 ≡ 1 −
SSres
SStot
Suppose R 2 = 0.49. This implies that 49% of the variability of the
dependent variable has been accounted for, and the remaining 51% of
the variability is still unaccounted for
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 455 / 463
Lecture 23: Regression Analysis (Conti...) Coe cient of Determination (R 2 )
Coe cient of Determination (Conti...)
R2 is a statistic that will give some information about the goodness
of t of a model
in regression, the R2 coe cient of determination is a statistical
measure of how well the regression predictions approximate the real
data points
an R2 of 1 indicates that the regression predictions perfectly t the
data
R2 increases as we increase the number of variables in the model (R
2
is monotone increasing with the number of variables included i.e., it
will never decrease)
an adjusted R2 is a modi cation of R2 that adjusts for the number of
explanatory terms in a model (p ) relative to the number of data
points (n)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 456 / 463
Lecture 23: Regression Analysis (Conti...) Adjusted R 2
Adjusted R 2
the adjusted R2 is de ned as
n−1
R̄ 2 = 1 − (1 − R 2 )
n−p−1
where p is the total number of independent variables in the model
(not including the constant term), and n is the sample size
the explanation of this statistic is almost the same as R2 but it
penalizes the statistic as extra variables are included in the model
R2 and R̄ 2 are also used for measuring goodness-of- t of the tted
model.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 457 / 463
Lecture 23: Regression Analysis (Conti...) Adjusted R 2
Exercises (Conti...)
1 The following sample of observations were randomly selected.
x 4 5 3 6 10
y 4 6 5 7 7
(a). Fit a model y on x
(b). Find the coe cient of determination. Interpret your ndings.
(c). Find the adjusted R 2 . Interpret your ndings.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 458 / 463
Lecture 23: Regression Analysis (Conti...) Adjusted R 2
Classroom Practice
1 The following sample of observations were randomly selected.
No. of TV Commercials (x ) 2 5 1 3 4 1 5 3 4 2
Total Sales(y ) 50 57 41 54 54 38 63 48 59 46
(a). Find the linear relationship between number of TV Commercials and total
sales.
(b). Fit a model y on x .
(c). Find the coe cient of determination. Interpret your ndings.
(d). Find the adjusted R 2 . Interpret your ndings.
(e). Predict (or forecast) total sales when x = 5.
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 459 / 463
Lecture 23: Regression Analysis (Conti...) Homework
Homework
HW: Read the Chapter 14 of the text book
Exercises: 47-51, pp.122-124
Exercises: 4-14, 18-21, pp.570-582
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 460 / 463
Lecture 24: Review Class
Lecture 24: Review Class
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 461 / 463
Lecture 24: Review Class
24 Lecture 24: Review Class
24.1 Syllabus for the Final Exam and Marks Distribution
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 462 / 463
Lecture 24: Review Class Syllabus for the Final Exam and Marks Distribution
Syllabus for the Final Exam
Final Exam (35%)
▸ Date: 17 December, 2022 (Saturday)
▸ Time: 14:00 pm- 16:00 pm
1 Normal Distribution (Lectures 13-14)
2 Interval Estimation (Lectures 17-18)
3 Test of Hypothesis (Lectures 19-20)
4 Correlation Analysis (Lecture 21)
5 Regression Analysis (Lectures 22-23)
Two Class Tests (15%+15%=30%)
One mid-term test (25%)
Class attendance and participation (10%)
Dr. Md. Rezaul Karim (Assoticate Professor, Department of Statistics, JU) Statistics Spring - 2023 463 / 463
You might also like
- Introduction To Statistics Fall 2020: Teacher Name: Dr. Saqib Ur RehmanNo ratings yetIntroduction To Statistics Fall 2020: Teacher Name: Dr. Saqib Ur Rehman3 pages
- Introduction To Statistics and Data AnalysisNo ratings yetIntroduction To Statistics and Data Analysis567 pages
- Semester Based Syllabus For The Course "B.A. Programme" StatisticsNo ratings yetSemester Based Syllabus For The Course "B.A. Programme" Statistics4 pages
- Department of Statistics Cotton University: Revised Syllabus According To NEP 2020No ratings yetDepartment of Statistics Cotton University: Revised Syllabus According To NEP 202095 pages
- B.A - B.SC - Statistics - Semester - Pattern2013 PDFNo ratings yetB.A - B.SC - Statistics - Semester - Pattern2013 PDF17 pages
- Elementary Statistical Methods 7th Edition - 678No ratings yetElementary Statistical Methods 7th Edition - 678383 pages
- Stat 20053 Statistical Analysis With Software Application PDF100% (1)Stat 20053 Statistical Analysis With Software Application PDF141 pages
- MTS-PST-311 Course Outline (BGEN3, BMEN3, and BMMP3) - 2024No ratings yetMTS-PST-311 Course Outline (BGEN3, BMEN3, and BMMP3) - 20248 pages
- Educational Statistics Course Outline 2nd Session 2018-2019No ratings yetEducational Statistics Course Outline 2nd Session 2018-20198 pages
- St. Joseph'S Degree & PG College: Statistics For ManagementNo ratings yetSt. Joseph'S Degree & PG College: Statistics For Management89 pages
- 2018 Revised CBCS Syllabus For BA and BSCNo ratings yet2018 Revised CBCS Syllabus For BA and BSC24 pages
- Introduction To Statistics - Course SyllabusNo ratings yetIntroduction To Statistics - Course Syllabus3 pages
- Basic Statistics 1st Edition Seemon ThomasNo ratings yetBasic Statistics 1st Edition Seemon Thomas84 pages
- SYLLBUS For English Test in A College or UniversityNo ratings yetSYLLBUS For English Test in A College or University1 page
- Business Statistics SIM Semester 1 2019: Welcome - Lecture 1: Ms. Kathryn Bendell EmailNo ratings yetBusiness Statistics SIM Semester 1 2019: Welcome - Lecture 1: Ms. Kathryn Bendell Email38 pages
- Client Fee Dependence & Audit IndependenceNo ratings yetClient Fee Dependence & Audit Independence9 pages
- Six Sigma: Define-Measure-Analyze-Improve-Control (DMAIC)No ratings yetSix Sigma: Define-Measure-Analyze-Improve-Control (DMAIC)21 pages
- Essential Math For AI Hala Nelson Instant DownloadNo ratings yetEssential Math For AI Hala Nelson Instant Download54 pages
- 1959 - Gordon Dividends, Earnings, and Stock Prices PDFNo ratings yet1959 - Gordon Dividends, Earnings, and Stock Prices PDF8 pages
- PDF Introduction To Statistics in Metrology Stephen Crowder Download100% (2)PDF Introduction To Statistics in Metrology Stephen Crowder Download65 pages
- Influence of HIV Testing On Knowledge of HIV AIDS Prevention Practices and Transmission Among Undergraduate Youths in North West UniNo ratings yetInfluence of HIV Testing On Knowledge of HIV AIDS Prevention Practices and Transmission Among Undergraduate Youths in North West Uni16 pages
- Abhilash Ganji: Sr. Data Analyst ProfileNo ratings yetAbhilash Ganji: Sr. Data Analyst Profile1 page
- A Quantitative Assessment of Student Performance and Examination FormatNo ratings yetA Quantitative Assessment of Student Performance and Examination Format10 pages
- K. Sam Shanmugan, Arthur M. Breipohl-Random Signals - Detection, Estimation and Data Analysis-Wiley (1988) PDF100% (4)K. Sam Shanmugan, Arthur M. Breipohl-Random Signals - Detection, Estimation and Data Analysis-Wiley (1988) PDF676 pages
- ECE 3040 Lecture 18: Curve Fitting by Least-Squares-Error RegressionNo ratings yetECE 3040 Lecture 18: Curve Fitting by Least-Squares-Error Regression38 pages
- Critical Thinking in Proposal Writing TrainingNo ratings yetCritical Thinking in Proposal Writing Training86 pages
- Data Analysis and Graphics Using R An Example Based Approach Third Edition John Maindonald Full100% (6)Data Analysis and Graphics Using R An Example Based Approach Third Edition John Maindonald Full105 pages
- Coursera Courses For IIM Interview Profile StrengtheningNo ratings yetCoursera Courses For IIM Interview Profile Strengthening2 pages
- MINIMUM DETECTABLE EFFECTS A Simple Way To Report The Statistical Power of Experimental DesignsNo ratings yetMINIMUM DETECTABLE EFFECTS A Simple Way To Report The Statistical Power of Experimental Designs10 pages
- New Strategies For Estimation of Cut and Fill Areas in Road Design With Different Ground Cross-Section OffsetsNo ratings yetNew Strategies For Estimation of Cut and Fill Areas in Road Design With Different Ground Cross-Section Offsets12 pages
