Introduction To Probability

Khris Griffis, Ph.D.

Lecture 02
CSULA: ME3040
1 Last
Last Time
Time
6 Stages Of A Statistical Investigation
6 Stages Of A Statistical Investigation

3
 Statistical Purpose
→ To answer a question about a population (of data).
In a perfect world, we would have access to the full population so we would be able to answer the question
based on data collected on all the observational units of the population. We would know the value of the
true parameter we are interested in.
But usually we just have one sample.
 Definitions
 Statistics Science of gathering, analyzing, interpreting,
communicating data
 Statistical Hypothesis Statement about a parameter of the data
 Dataset Collection of measurements from multiple
Observational Units
 Observational unit Entity from which data was collected
 Variable Come in types categorical or quantitative
 Variable relationships Response variable depend on explanatory variable
 Outlier Markedly different from the rest
 Population All observational units, ever
 Sample A subset of a population we use to make inferences
about the population
2 Frequentism,
Introduction
Introduction To

Frequentism, Bayesianism,
Bayesianism, Set
Combinatorics
Combinatorics
To Probability
Probability

Set Theory
Theory And
And
 Frequentism and Bayesian Probability
The Frequentist's Approach The Bayesian Approach
The frequentist's perspective emphasizes the Bayesian probability focuses on subjective belief
importance of repeated trials in understanding rather than objective data.
probability. Defines probability as a measure of belief, 0 to
Views probability as long-term event 1 scale.
frequency. Subjective, based on opinion rather than
Based on repeated, identical trials. inherent system traits.
 What is Probability?
Probability is the measure of the likelihood that an event will occur. It quantifies uncertainty and
is expressed as a number between 0 and 1, where 0 indicates impossibility and 1 indicates certainty.
Terminology Meaning

The set of all possible outcomes of a probabilistic experiment. For

Sample Space (𝑆): example, in a quality test of a car engine, the sample space might
include outcomes like 'Pass' and 'Fail'.
A subset of the sample space. An event can consist of one or more
Event: outcomes. For instance, the event 'Engine Fails' includes all
outcomes where the engine fails the quality test.
The likelihood of an event occurring, which is a number between
0 and 1. If 𝑃 (𝐴) = 1, the event is certain to happen, and if 𝑃 (𝐴)
Probability of an Event (𝑃 (𝐴)): = 0, the event is impossible. For example, if the probability of an
engine passing the quality test is 0.95, it can be written as
𝑃 (Engine Passes) = 0.95.
 Approaches
Probability theory is a fundamental part of mathematics and statistics that deals with the likelihood of
different outcomes in various scenarios. There are three primary approaches to understanding and
calculating probability:
Approach Description
Based on personal judgment and available information. It is often used in scenarios where hard data is
Subjective
scarce, and decisions are made based on beliefs or expert knowledge.
Assumes that all outcomes in a sample space are equally likely. It is best suited for situations where you
Classical can clearly define all possible outcomes, and each outcome has the same chance of occurring, i.e.,
symmetrical weight.
Relies on actual data collected from experiments or observations. Empirical probability is calculated by
Empirical
dividing the number of times an event occurs by the total number of trials or observations.
 Classical Probability
Probability is a measure of the likelihood that an event will occur.
Number of outcomes in event
𝑃 (𝐴) = Number of outcomes in sample space
In the context of mechanical engineering, probability can be used to assess the reliability of
systems and components.
For example, if a gear in a transmission system has a 1 in 100 chance of failing under certain
conditions, its probability of failure is 0.01.
 Classical Probability
Coin Flip Six-Sided Die
A fair six-sided die has six outcomes: 1, 2, 3, 4, 5, 6.
The probability of rolling a specific number (e.g., 4)
A fair coin has two equally likely outcomes: is:
Heads or Tails.
The probability of getting Heads (H) is: 1
𝑃 (4) = 6
1
𝑃 (𝐻 ) = 2 The probability of rolling an even number (2, 4, or
6) is:
The probability of getting Tails (T) is:
𝑃 (Even) = 𝑃 (2) + 𝑃 (4) + 𝑃 (6)
1
𝑃 (𝑇 ) = 2 1 1 1 3
=6+6+6=6
1
=2
 Empirical Probability
Empirical probability is calculated based on observed data or past experiences. It measures the
likelihood of an event by dividing the number of observed occurrences by the total number of
observations.
Relative frequency, the ratio of an event's occurrences to total trials, forms the empirical basis for
calculating an event's probability.

Relative Frequency = Frequency of the event occurring

Total number of trials
Example: Consider a biomechanical experiment where a prosthetic knee is subjected to repeated stress tests.
Out of 500 tests, the knee joint fails 5 times. The relative frequency of failure is calculated as:
5
Relative Frequency of Failure = 500 = 0.01
This means that the probability of failure in a single stress test, based on past data, is 1%.
 Empirical Probability: Examples
Space Shuttle Mission Failures Bolt Production
Following the Columbia disaster on February 1, 2003, Example: In a factory, a machine produces bolts. After
NASA's second in 113 missions, we estimate the probability producing 10,000 bolts, it is observed that 20 are defective.
of future mission success. The relative frequency of producing a defective bolt is:
Defining P as probability and P(A) as success probability:
20
Relative Frequency = 10,000 = 0.002
111
𝑃 (𝐴) = 113 = 0.98
This indicates that, based on past production, there is a 0.2%
This suggests a 0.98 probability of successful completion for
probability of the machine producing a defective bolt.
future space shuttle missions.
The Law of Large Numbers states that as the number of trials increases, the relative frequency of
an event gets closer to the true probability of the event.
3 An
Set
Set Theory

An Introduction
Theory

Introduction To
To Belonging
Belonging
Intersection of Set Theory and Probability
Set theory and probability form the mathematical backbone of analyzing and predicting outcomes
in various fields, providing tools to quantify uncertainty and make informed decisions.

🌟 Set Theory: A fundamental branch of mathematics

focused on the study of sets, collections of distinct objects.
Set theory underpins probability by defining events as sets
and exploring relationships through operations like union,
intersection, and complement.
🌟 Combinatorics: In the context of probability,
combinatorics involves the study of counting,
arrangement, and combination of elements, crucial for
calculating the likelihood of various events and
understanding the structure of different outcomes.
Rules For Calculations
Rules In Detail: Special Rule of Addition
Rules In Detail: General Rule of Addition
 Rules In Detail: Multiplication
Special General
This rule calculates the probability of two independent This rule calculates the probability of two events X and Y
events X and Y occurring together. It's the product of their occurring together, accounting for the possibility of
individual probabilities. dependence between them.
Formula: 𝑃 (𝑋 ∩ 𝑌 ) = 𝑃 (𝑋) × 𝑃 (𝑌 ) for independent Formula: 𝑃 (𝑋 ∩ 𝑌 ) = 𝑃 (𝑋) × 𝑃 (𝑌 |𝑋), where Y is
conditional on X.
events X and Y.
Consider two events in a mechanical system with a dependent
Consider two independent events in a mechanical system:
relationship:
Event X: A sensor operates nominally with 𝑃 (𝑋) = 0.9. Event X: A machine starts successfully with 𝑃 (𝑋) = 0.85.
Event Y: A valve operates nominally with 𝑃 (𝑌 ) = 0.8. Event Y: The cooling system engages with 𝑃 (𝑌 |𝑋) = 0.9, i.e., it
starts 90% of the time after the machine starts.
The probability of both the sensor activating and the valve
The probability of both the machine starting and the cooling
opening successfully is:
system engaging is:
𝑃 (𝑋 ∩ 𝑌 ) = 𝑃 (𝑋) × 𝑃 (𝑌 ) = 0.9 × 0.8 = 0.72. ∩
𝑃 (𝑋 𝑌 ) = 𝑃 (𝑋) × 𝑃 (𝑌 |𝑋) = 0.85 × 0.9 = 0.765.
 Multiple Independent Events
Independent Events Multiple Independent Events
If two events, 𝐴 and 𝐵, are independent, the probability of If you have more than 2 independent events, say 𝐴, 𝐵,
both events occurring is the intersection of their individual and 𝐶 , and you want the probability that all these events
probabilities. occur, you multiply the probabilities of each event.
∩
Formula: 𝑃 (𝐴 𝐵) = 𝑃 (𝐴) × 𝑃 (𝐵) ∩ ∩
Formula: 𝑃 (𝐴 𝐵 𝐶 ) = 𝑃 (𝐴) × 𝑃 (𝐵) × 𝑃 (𝐶 )
Simply, the probability of both events occurring is the
Example: Rolling 3 six-sided dice
product of their individual probabilities.
Example: Flipping a coin twice For a specific outcome, say the dice land on 3,5,4 in no
Each flip is independent of the last. specific order, the process is the same.
The probability of getting heads on each flip is 𝑃 (𝐻 ) The probability of rolling a specific number is: 𝑃 (#) = 16
= 12 . The probability of rolling 3 dice and getting
Since the two flips are independent, the probability of (3, 5, 4) is:
getting heads both times is: 𝑃 (3,5,4) = 𝑃 (3) × 𝑃 (5) × 𝑃 (4)
1 1 1 1 1 1 1
= 6 × 6 × 6 = 216
𝑃 (𝐻1 ∩ 𝐻2 ) = 𝑃 (𝐻1 ) × 𝑃 (𝐻2 ) = 2 × 2 = 4
 Marginal Probabilities
What are Marginal Probabilities ∩       ∑
1
Marginal probability is the probability of a single  6 1/36 1/36 1/36 1/36 1/36 6/36
event occurring, summed over all possible outcomes of × 61
another variable.  1/36 1/36 1/36 1/36 1/36 1/36 6/36
For example, in the context of rolling two dice, the  1/36 1/36 1/36 1/36 1/36 1/36 6/36
marginal probability of a die throw can be found by
 1/36 1/36 1/36 1/36 1/36 1/36 6/36
summing the probabilities of one die face across all
outcomes of the other die.  1/36 1/36 1/36 1/36 1/36 1/36 6/36
 1/36 1/36 1/36 1/36 1/36 1/36 6/36
∑ 6/36 6/36 6/36 6/36 6/36 6/36 36/36
How do we calculate Marginal Probabilities for throwing 2 dice
The sum of the marginals is equal to 1!
 Marginal Probabilities
Consider rolling two 6-sided dice:
Let 𝐴 be the event the sum of the roll is 7.
Let 𝐵 be the event at least one face shows a 4. ∩       ∑
≈
The probability of 𝐴 (sum equals 7) is: 𝑃 (𝐴) = 366 = 61 0.167  1/36 1/36 1/36 1/36 1/36 1/36 6/36
The probability of 𝐵 (at least one die shows a 4) is: 𝑃 (𝐵) = 36
11
≈ 0.306  1/36 1/36 1/36 1/36 1/36 1/36 6/36
The probability of both 𝐴 and 𝐵 occurring (sum equals 7 and at  1/36 1/36 1/36 1/36 1/36 1/36 6/36
least one die shows a 4) is: 𝑃 (𝐴 ∩ 𝐵) = 36 = 18 ≈ 0.056
2 1
 1/36 1/36 1/36 1/16 1/36 1/36 6/36
The probability of 𝐴 or 𝐵 occurring (sum equals 7 or at least
one die shows a 4) is calculated as:  1/36 1/36 1/36 1/36 1/36 1/36 6/36

𝑃 (𝐴 ∪ 𝐵) = 𝑃 (𝐴) + 𝑃 (𝐵) − 𝑃 (𝐴 ∩ 𝐵)  1/36 1/36 1/36 1/36 1/36 1/36 6/36

𝑃 (𝐴 ∪ 𝐵) = 0.167 + 0.306 − 0.056 ≈ 0.417

∑ 6/36 6/36 6/36 6/36 6/36 6/36 36/36
 Probabilty (Definitions)
The measure of the likelihood that an event will occur. Probability is quantified as a
 Probability
number between 0 and 1, where 0 indicates impossibility and 1 indicates certainty.
The set of all possible outcomes of a probabilistic experiment. For example, in a quality test
 Sample Space (𝑆)
of a car engine, the sample space might include outcomes like 'Pass' and 'Fail'.
A subset of the sample space (𝑆) that consists of one or more outcomes. An event can be
 Event
something like 'Engine Fails' in a quality test.
A probability approach where all outcomes in the sample space are assumed to be equally
likely. The probability of an event 𝐴 is calculated as:
 Classical Probability
Number of outcomes in event
𝑃 (𝐴) = Number of outcomes in sample space

Probability based on observed data or past experiences, calculated by dividing the number
 Empirical Probability
of observed occurrences by the total number of observations.
A branch of mathematics focused on the study of sets, collections of distinct objects. Set
 Set Theory theory underpins probability by defining events as sets and exploring relationships through
operations like union, intersection, and complement.
Lecture 02 Khris Griffis ©2024