STATISTICS IS THE GRAMMAR OF SCIENCE
PROBABILITY AND STATISTICS
LECTURE – 1
INTRODUCTION TO STATISTICS
PREPARED BY
HAZBER SAMSON
FAST NUCES ISLAMABAD
MT-2005 PROBABILITY AND STATISTICS INTRODUCTION TO STATISTICS
INTRODUCTION TO STATISTICS
STATISTICS Statistics is a Science used to collect, organize, present, analyze and
interpret data to make decisions.
TYPES OF STATISTICS Basically there are two types of statistics.
1. Descriptive Statistics 2. Inferential Statistics
DESCRIPTIVE STATISTICS descriptive statistics consists of methods used to organize,
preset and summarize data by using tables, graphs and summary sheets.
INFERENTIAL STATISTICS Inferential statistics consists of methods used to find out
something about a population based on a sample.
IMPORTANCE OF STATISTICS
1. Statistics is used in different fields of Sciences like Social Sciences, Plant
Sciences, Physical Sciences and Medical sciences.
2. It plays an important role in planning and helps the government in formulating the
policies.
3. It plays an important role in Business, industry and Banking sector.
4. statistics present the data in comparable form so it helps us comparing past
results with present.
5. Forecasting is the main objective of statistics. Forecasting means estimating
future values with the help of past data.
BASIC TERMS IN STATISTICS
POPULATION A collection of all possible individuals, objects or measurements of
interest is called a population. For example set of students in a college.
SAMPLE A portion or part of a population of interest is called a sample. For example set
of students of Ist year class from a University.
PARAMETER Any numerical; value computed from the population is called a parameter.
Parameters are fixed quantities.
STATISTIC Any numerical value computed from the sample is called a statistic.
Statistics are variable quantities because they vary from sample to sample.
FIGURE 1.1 Relationship between population and sample
1
Page
PREPARED BY HAZBER SAMSON SCIENCES AND HUMANITIES DPT FAST ISLAMABAD
MT-2005 PROBABILITY AND STATISTICS INTRODUCTION TO STATISTICS
DATA AND TYPES OF DATA
DATA Numerical facts or observations are collectively called data. A single numerical
fact is called datum. There are different types of data.
UNIVARIATE DATA Data that represents observations on one variable that are
measured in the same units is called Univariate data.
BIVARIATE DATA Data that represents observations on two variables that are
measured in the different units is called Bivariate data.
MUTIVARIATE DATA Data that represents observations on more than two variables
that are measured in the different units is called Multivariate data.
PRIMARY DATA Data that have been originally collected and have not undergone any
sort of statistical treatment is called a primary data. For example marks of all the
students in a class.
SECONDARY DATA Data that have undergone any sort of statistical treatment is called
secondary data. For example percentage marks of each student in the class.
SOURCES OF PRIMARY DATA There are different sources of Primary Data.
Through investigation
Through Questionnaire
Through Local Sources
Through Telephone
Through Internet
SOURCES OF SECONDARY DATA There are different sources of Secondary Data.
Government Organizations
Semi-government Organizations
Research Organizations
Newspapers
Internet
CROSS-SECTION VERSUS TIME-SERIES DATA Based on the time over which they
are collected, data can be classified as either cross-section or time-series data.
CROSS-SECTION DATA Data collected on different elements at the same point in time
or for the same period of time are called cross-section data.
TIME-SERIES DATA Data collected on the same element for the same variable at
different points in time or for different periods of time are called time-series data.
2
Page
PREPARED BY HAZBER SAMSON SCIENCES AND HUMANITIES DPT FAST ISLAMABAD
MT-2005 PROBABILITY AND STATISTICS INTRODUCTION TO STATISTICS
VARIABLE AND TYPES OF VARIABLES
VARIABLE A variable is a characteristic under study that assumes different values for
different elements. In contrast to a variable, constant assumes only one value ie its value
is fixed.
Types of Variables Basically there are two types of variables.
1. Qualitative Variables 2. Quantitative Variables
QUALITATIVE VARIABLE A variable that can not be measured numerically but can be
classified into two or more nonnumeric categories is called a qualitative variable or
categorical variable or an attribute. The data collected on qualitative variable is called
qualitative data. For example gender, religious affiliation and eye color etc.
QUANTITATIVE VARIABLE A variable that can be measured numerically is called a
quantitative data. The data collected on a quantitative variable is called quantitative data.
For example Incomes, heights, gross sales, prices of homes, number of accidents etc.
There are two types of quantitative variables
1. Discrete Variable 2. Continuous Variable
DISCRETE VARIABLE A variable is said to be discrete if it can assume only certain
values in a given interval. These values are countable.
For example Number of bedrooms in a house, Number of doctors in a hospital etc
CONTINUOUS VARIABLE A variable is said to be continuous if it can assume any
value in a given interval. These values are not countable.
For example temperature at a place, height of a person, speedometer etc
FIGURE 1.2 Summary of the types of variables
3
Page
PREPARED BY HAZBER SAMSON SCIENCES AND HUMANITIES DPT FAST ISLAMABAD
MT-2005 PROBABILITY AND STATISTICS INTRODUCTION TO STATISTICS
MEASUREMENT SCALES OF VARIABLES
Measurement means assigning numbers to observations or objects and scaling is a
process of measuring. Basically there are four scales of measurement w.r.t any data set
1. Ratio Scale
2. Interval scale
3. Ordinal Scale
4. Nominal Scale
RATIO SCALE Suppose that X is a variable taking two values x1 and x2 . If it satisfy the
following properties it can be referred as ratio scale.
P 1 : Ratio is meaningful ie x2 x1 is meaningful.
P 2 : Distance is meaningful ie x2 x1 is meaningful.
P 3 : There exists natural ordering. ie x2 x1
EXAMPLES of ratio scale are Age, Weight, Height, Time, salary, Distance.
It is a special kind of an interval scale where the scale of measurement has a true zero
point as its origin.
The Ratio scale data has the following properties.
1. Data categories are mutually exclusive and exhaustive.
2. Data categories are scaled according to the amount of the characteristic they
possess.
3. Equal difference in the characteristic are represented by equal difference ij the
numbers assigned to the categories.
4. The point 0 reflects the absence of the characteristic.
INTERVAL SCALE Suppose that X is a variable taking two values x1 and x2 . If it satisfy
the 2nd and 3rd properties of ratio scale than it can be referred as Interval scale.
P 1 : Distance is meaningful ie x2 x1 is meaningful.
P 2 : There exists natural ordering. ie x2 x1
EXAMPLES of interval scale are Temperature, IQ Score
A measurement scale possessing a constant interval size but not a true zero point, is
called an interval scale.
The Interval scale data has the following properties.
1. Data categories are mutually exclusive and exhaustive.
2. Data categories are scaled according to the amount of the characteristic they
possess.
4
3. Equal difference in the characteristic are represented by equal difference in the
Page
numbers assigned to the categories.
PREPARED BY HAZBER SAMSON SCIENCES AND HUMANITIES DPT FAST ISLAMABAD
MT-2005 PROBABILITY AND STATISTICS INTRODUCTION TO STATISTICS
ORDINAL SCALE Suppose that X is a variable taking two values x1 and x2 . If it satisfy
only 3rd property of ratio scale than it can be referred as Ordinal scale.
P 1 : There exists natural ordering. ie x2 x1
EXAMPLES of ordinal scale are
(1) Grades of students (A,B,C,D,E,F)
(2) Ranking of Universities (1st, 2nd, 3rd)
(3) Socio Economic Status (Poor, Middle class, Rich)
The ordinal scale data has the following properties.
1. Data categories are mutually exclusive and exhaustive.
2. Data categories have a logical order.
NOMINAL SCALE Nominal scale does not exhibit any property of ratio scale. It is a
categorical variable,
EXAMPLES of Nominal scale are
(1) Gender
(2) Religion
(3) Nationality
(4) Eye color
(5) Marital Status
In this scale observations are classified into mutually exclusive qualitative categories.
The nominal scale data has the following properties.
1. Data categories are mutually exclusive.
2. Data categories have no logical order.
FIGURE 1.3 Summary and Examples of the Characteristics for Levels of Measurement
5
Page
PREPARED BY HAZBER SAMSON SCIENCES AND HUMANITIES DPT FAST ISLAMABAD
MT-2005 PROBABILITY AND STATISTICS INTRODUCTION TO STATISTICS
IMPORTANT NOTATIONS
SUM It is a Greek letter (read as sigma) and is used as a short-hand notation for
sum.
i n
In general y1 y 2 ... y n y i
i 1
For example if y1 2 , y 2 3 and y3 5
i 3
then y
i 1
i y1 y 2 y3 2 3 5 10
PRODUCT It is a Greek letter (read as pi) and is used as a short hand notation for
product.
i n
In general y1 y 2 ... y n y i
i 1
For example if y1 2 , y 2 3 and y3 5
i n
then y
i 1
i y1 y 2 y 3 2 3 5 30
SIGNIFICANT FIGURES Those figures in a number which give its information other than
its magnitude are called significant figures.
EXAMPLES
1. 26.2 contains 3 significant figures.
2. 1225 contains 4 significant figures.
3. 0.95 contains 2 significant figures.
4. 0.0037 contains 2 significant figures.
5. 0.001592 contains 4 significant figures.
ROUNDING OF FIGURES In order to express figures to smaller number of significant
figures we usually round off the numbers. In rounding off the figures we examine the last
significant figure. So
1. If it is less than 5 last significant figure will remain the same.
2. If it is greater than 5 than last significant figure is increased by 1.
3. If it is exactly 5 then
(a) Increase the last significant figure by one if it is an odd number.
(b) The last significant figure remains same if it is an even number.
EXAMPLES
1. 523 becomes 520
2. 526 becomes 530
3. 1975 becomes 1980
4. 1962 becomes 1962
5. 4.345 becomes 4.32
6
Page
PREPARED BY HAZBER SAMSON SCIENCES AND HUMANITIES DPT FAST ISLAMABAD
