JOINT PROBABILITY
DISTRIBUTION
JM TROY M. MABIA
BSEE-2B
Objectives
At the end of the lesson, students should be able to:
1. Define and differentiate between one random variable and two (or more)
random variables.
2. Construct and interpret joint probability distribution tables.
3. Determine and compute marginal probability distributions from a joint
distribution.
4. Calculate and interpret conditional probability distributions.
5. Analyze situations involving more than two random variables.
6. Compute and interpret linear functions of random variables
7. Evaluate and describe general functions of random variables.
8. Apply probability distribution concepts to solve real-life problems
involving uncertainty.
Joint Probability Distribution
A Joint Probability Distribution describes the probability that two (or
more) random variables occur at the same time.
If we have two random variables:
X
Y
The Joint Probability is written as:
P(X=x, Y=y)
It answers the question:
What is the probability that X takes value x and Y takes value y
simultaneously?
DISCRETE JOINT PROBABILITY DISTRIBUTION
If X and Y are discrete random variables, the Joint Probability
Distribution is usually presented in a table form.
Example: Coin and Die
Let:
X= number of heads when flipping 1 coin
Y= number on a fair die
Since coin and die are independent:
P(X=x, Y=y)= P(X=x)P(Y=y)
DISCRETE JOINT PROBABILITY DISTRIBUTION
Example 2: Joint Distribution Table
Given the table below, (A) interpret each value carefully and (B)
check whether the table is a valid joint distribution.
y
A. We will be using P(X=x, Y=y)
B. We will be using ∑x∑yP(x,y)=1
CONTINUOUS JOINT PROBABILITY
DISTRIBUTION
It describes the probability of two continuous variables happening
together.
Let say for example:
X= time (seconds)
Y= speed (m/s)
Since time and speed can take any decimal value, they are
continuous.
For continuous variables:
P(X=x, Y=y)=0
CONTINUOUS JOINT PROBABILITY
DISTRIBUTION
The probability at one exact point is always zero (0). Instead, we find
probability over a range (an area).
We use a function called f(x,y), this is called the Joint Probability
Density Function (Joint PDF). It does not directly give probability. To
get the probability, we integrate.
P(a≤X≤b,c≤Y≤d)
We compute: Example:
Find the probability that both X and Y are between 0 and
0.5.
So:
P(0≤X≤0.5,0≤Y≤0.5)
MARGINAL PROBABILITY DISTRIBUTION
Marginal probability tells us the probability of one variable alone,
taken from a joint distribution.
If we have two random variables:
X and Y
The joint distribution gives:
P(X=x,Y=y)
But sometimes we only want:
P(X=x). That is called the Marginal Probability Distribution of X.
MARGINAL PROBABILITY DISTRIBUTION
Why is it call Marginal? Because when joint distributions are written
in a table, we compute it by summing values along the margins
(edges) of the table.
Formula:
P(X=x)= x∑P(X=x)
P(Y=y)= y∑P(Y=y)
Example:
Given the table below, Find (A) the Marginal Distribution of X and its
Marginal Distribution Table, and (B) Find the Marginal Distribution of
Y and its Marginal Distribution Table.
MARGINAL PROBABILITY DISTRIBUTION
x
CONDITIONAL PROBABILITY DISTRIBUTION
Conditional Probability Distribution is the probability distribution of
one random variable after we already know the value of another
random variable.
It answers questions like:
What is the probability that a machine fails given that temperature
is high?
What is the probability of passing given that a student studied?
It focuses on updating probabilities when new information is known.
CONDITIONAL PROBABILITY DISTRIBUTION
Conditional Probability Formula
The conditional probability of X given Y=y is:
Where:
CONDITIONAL PROBABILITY DISTRIBUTION
Example: Study Hours and Passing Exam
Let:
X= 1 if student passed, 0 if failed
Y= 1 if studied, 0 if did not study
Joint Probability Table:
Find the (A) Marginal Probability of Studying and (B) Find the
Conditional Probability.
JOINT PROBABILITY DISTRIBUTION OF MORE
THAN TWO RANDOM VARIABLES
The joint probability distribution of more than two random variables
describes the probability that all variables take specific values at the
same time.
If we have three random variables:
X, Y, Z
The joint probability is written as:
Discrete case:
P(X=x,Y=y,Z=z)
Continuous case:
f X,Y,Z(x,y,z)
JOINT PROBABILITY DISTRIBUTION OF MORE
THAN TWO RANDOM VARIABLES
In discrete case of three random variables, it must satisfy:
-Non-negativity: P(x,y,z)≥0
-Total probability is equal to 1
Example:
Given the data in table below:
Suppose:
X = Machine Condition (1 = Good, 0 = Bad)
Y = Operator Skill (1 = Skilled, 0 = Not Skilled)
Z = Product Quality (1 = Good, 0 = Defective)
JOINT PROBABILITY DISTRIBUTION OF MORE
THAN TWO RANDOM VARIABLES
Find (A) the Marginal Distributions
of X when P(X=1) and (B) the
Conditional Distribution of the
probability of good product given
good machine and skilled operator.
LINEAR FUNCTIONS OF RANDOM VARIABLES
A linear function of random variables is a new random variable formed by
taking a linear combination of one or more random variables.
If we have two random variables:
X and Y
Their joint probability distribution describes how they behave together.
A linear function has the form:
Z=aX+bY+c
Where:
a,b,c are constants
X,Y are random variables
LINEAR FUNCTIONS OF RANDOM VARIABLES
Expected Value: E[aX+bY+c]= aE[X]+bE[Y]+c
or
Example:
If: E[X]=3, E[Y]=5
Let: 2X-Y
Then: E[Z]=2(3)−5=1
E[Z]=1
Probability Distribution of Z: Use the linear function form
Variance: OR
LINEAR FUNCTIONS OF RANDOM VARIABLES
Suppose two discrete random variables X and Y have the following joint
probability distribution:
Let the linear function be: Z=2X+Y
Find:
1. The probability distribution of Z
2. E[Z]
3. Var(Z)
GENERAL FUNCTIONS OF RANDOM VARIABLES
A general function of a random variable is a new random variable created by
applying any mathematical function to an existing random variable.
Formally, if X is a random variable and g is a function, then
Y=g(X)
Probability Distribution of Y: Compute using the form Y=g(X)
Expected Value E[Y]:
Variance of Y Var[Y]:
GENERAL FUNCTIONS OF RANDOM VARIABLES
Example:
Let X be a discrete random variable with the following probability distribution
table:
Defined by a function: Y=g(X)=3X+1
Find:
1. The probability distribution of Y
2. E[Y] (expected value of Y)
3. Var(Y) (variance of Y)
References:
[Link]
[Link]
Thank
You
[Link]