MAT3003 Probability, Statistics and Reliability

Bivariate Random Variables

Dr.E.Prasad
Asst Professor, Dept of Mathematics
VIT Bhopal University

Spring 2024-25

Module 3 Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Syllabus

Joint density function, Joint probability distribution, Marginal Probability

Distribution, Conditional Probability Distribution, Covariance, Correlation
Coefficient, Regression Analysis (partial and multiple correlation).

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Joint Distributions of Discrete Random Variables

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Two Dimentional(Joint) Random Variable-Discrete

If all values of ( X, Y ) are countable (discrete random variable),then its probability mass

function defined as P( X , Y ) with following conditions are satisfies

1. P xj , yj ≥ 0, ∀ i, j

2. σxi σyi P xi , yi = 1

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables
𝐋𝐢𝐬𝐭 𝐨𝐟 𝐅𝐨𝐫𝐦𝐮𝐥𝐚

1. Marginal Functions

𝑎) 𝑃𝑋 𝑥𝑖 = ෍ 𝑃(𝑥𝑖 , 𝑦𝑖 ) 𝑏) 𝑃𝑌 𝑦𝑖 = ෍ 𝑃(𝑥𝑖 , 𝑦𝑖 )
𝑦𝑖 𝑥𝑖

2. Conditional Distribution
𝑃(𝑋=𝑥𝑖 ,𝑌=𝑦𝑖 ) 𝑃(𝑋=𝑥𝑖 ,𝑌=𝑦𝑖 )
a) P(𝑋/𝑌) = 𝑃𝑌 𝑦𝑖
b) P(𝑌/𝑋)= 𝑃𝑋 𝑥𝑖

3.Independence

𝑃(𝑋 = 𝑥𝑖 , 𝑌 = 𝑦𝑖 )= 𝑃𝑋 𝑥𝑖 * 𝑃𝑌 𝑦𝑖

4.Cumulative Distribution Function of ( X, Y ) is defined as

𝐹𝑋 𝑥𝑗 , 𝑦𝑗 = σ𝑥𝑖 σ𝑦𝑖 𝑃(𝑥𝑖 ≤ 𝑥𝑗 , 𝑦𝑖 ≤ 𝑦𝑗 )

5. Formula

𝑎) 𝐸 𝑋/𝑌 = ෍ 𝑥𝑖 𝑃(𝑋 /𝑌) 𝑏) 𝐸 𝑋 = ෍ 𝑥𝑖 𝑃𝑋 𝑥𝑖

𝑥𝑖 𝑥𝑖

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example3:

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables
Example4:
From the following joint distribution of X and Y find the marginal distributions.

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables
Example5:

Ans2: 1/12

Example6

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example7:

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example8:

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example9:

Example10:
Three fair coins are tossed. Let 𝑋 denote the number of heads on the first two coins,
let Y denote the number of tails on the last two coins .let Z denote the number of heads on
the last two coins.
a) Find the joint probability mass function of 𝑋 and Y and X and Z
b) Find the Probability of Y given X=1
c) Find the Probability of X given Z=1

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

JOINT DISTRIBUTIONS OF CONTINUOUS RANDOM VARIABLES

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Two Dimentional(Joint) Random Variable − Continuous

If all values of ( X, Y ) are countable (continuous random variable),then its probability joint

density function defined as f( x , y ) or 𝑓𝑥𝑦 𝑥, 𝑦 with following conditions are satisfies

1. f x, 𝑦 ≥ 0, ∀ x,y

∞ ∞
2. ‫׬‬−∞ ‫׬‬−∞ f( x , y )𝑑𝑥𝑑𝑦 = 1

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables
𝐋𝐢𝐬𝐭 𝐨𝐟 𝐅𝐨𝐫𝐦𝐮𝐥𝐚

1. Marginal Functions
∞ ∞
𝑎) 𝑓𝑋 𝑥 = 𝑓 𝑥 = න 𝑓 𝑥, 𝑦 𝑑𝑦 𝑏) 𝑓𝑌 𝑦 = 𝑓 𝑦 = න 𝑓 𝑥, 𝑦 𝑑𝑥
−∞ −∞

2. Conditional Distribution
𝑓(𝑥,𝑦) 𝑓(𝑥,𝑦)
a) f(𝑋/𝑌) = b) f(𝑌/𝑋) =
𝑓𝑌 𝑦 𝑓𝑋 𝑥

3.Independence
𝑓 𝑥, 𝑦 = 𝑓𝑋 𝑥 * 𝑓𝑌 𝑦

4.Cumulative Distribution Function of ( X, Y ) is defined as

𝑥
𝑗 𝑗 𝑦 𝜕2 𝐹𝑋𝑌 𝑥,𝑦
𝐹𝑋𝑌 𝑥𝑗 , 𝑦𝑗 = ‫׬‬−∞ ‫׬‬−∞ f( x , y )𝑑𝑥𝑑𝑦 Note: = 𝑓(𝑥, 𝑦)
𝜕𝑥𝜕𝑦

5. Formula 𝑎 ∞
𝑃(𝑋 < 𝑎, 𝑌 > 𝑏) ‫׬‬−∞ ‫ 𝑏׬‬f( x , y )𝑑𝑥𝑑𝑦
𝑎) 𝑃 𝑋 < 𝑎/𝑌 > 𝑏 = = ∞ ∞
𝑃(𝑌 > 𝑏) ‫׬‬−∞ ‫ 𝑏׬‬f( x , y )𝑑𝑥𝑑𝑦
∞
b)P(X>a)= ‫𝑥𝑑 𝑥 𝑋𝑓 𝑎׬‬
∞ ∞
c) E( Y/𝑋)= ‫׬‬−∞ 𝑦𝑓 𝑦/𝑥 𝑑𝑦 d) E( X)= ‫׬‬−∞ 𝑥 𝑓𝑋 𝑥 𝑑𝑥

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example1

1/4

Example2:

Example3:

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example1

1/4

Example2:

Example3:

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables
Example4:

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables
Example5:

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example6:

Example7:

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example8:

17/72

Example9: Verify the following

i)

ii)

iii)

Example10:

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example11:

Example12:

a) 10
b)
5 2
c) 12
𝑥
d) 1/4
e) E(X),E(Y) and E(XY)

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Covariance

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Introduction

Covariance is a measure of the relationship between two random variables and to

what extent, they change together

Types of Covariance
Covariance can have both positive and negative values. Based on this, it has two
types:
1. Positive Covariance
2. Negative Covariance

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Covariance of X and Y

1. If cov(X, Y) is greater than zero, then we can say that the covariance for any two
variables is positive and both the variables move in the same direction.
2. If cov(X, Y) is less than zero, then we can say that the covariance for any two variables
is negative and both the variables move in the opposite direction.
3. If cov(X, Y) is zero, then we can say that there is no relation between two variables.

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Properties of Covariance
1. It is a measure to show the extent to which given two random variables change
with respect to each other.
2. It is a measure of correlation.
3. The value of covariance lies between -∞ and +∞.
4. It indicates the direction of the linear relationship between the given two
variables.

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

(6)

(7)

(8)

(9)

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables
Formula
Formula: Cov(X,Y)=E(XY)-E(X)E(Y)

Case1: If all values of ( X, Y ) are countable (Discrete Random Variable), P xj , yj ≥ 0, ∀ i, j

a) E(X)=σ𝑥𝑖 σ𝑦𝑖 𝑥𝑖 𝑃( xi , yi )

b) E(y)=σ𝑥𝑖 σ𝑦𝑖 𝑦𝑖 𝑃( xi , yi )

c) E XY = σxi σyi xi yi P xi , yi

Case2: If all values of ( X, Y ) are countable (Continuous Random Variable), f xj , yj ≥ 0, ∀ i, j

∞ ∞
a) E(X)=‫׬‬−∞ ‫׬‬−∞ 𝑥𝑓 𝑥, 𝑦 𝑑𝑦 dx
∞ ∞
b) E(Y)=‫׬‬−∞ ‫׬‬−∞ 𝑦𝑓 𝑥, 𝑦 𝑑𝑦dx
∞ ∞
c) E XY = ‫׬‬−∞ ‫׬‬−∞ 𝑥𝑦(𝑓 𝑥. 𝑦 𝑑𝑥𝑑𝑦
Case3:For a given table x 𝑥1 𝑥2 𝑥3 .. 𝑥𝑛
y 𝑦1 𝑦2 𝑦3 .. 𝑦𝑛

1 𝑛
Cov(x,y)= σ 𝑥𝑦 − 𝑥ҧ 𝑦ത
𝑛 𝑖=1 𝑖 𝑖

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example :Find Cov(X,Y) of the following

1.
a) E(X)=1/2
b) E(Y)=3/2 ∴ Cov(X,Y)=3/4
c) E XY = 1

2.

a) E(X)=7/2
b) E(Y)=9/4 ∴ Cov(X,Y)= 5/8
c) E XY = 17/2

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

3. Suppose X and Y are continuous random variables with joint PDF

f(x,y) = 3x, where 0 ≤ y ≤ x+1, 0 ≤ x ≤ 1. What is the covariance of X and Y?

a) E(X)=7/4
∴ Cov(X,Y)= -347/160
b) E(Y)=17/8
c) E XY = 31/20

4. Suppose X and Y are continuous random variables with joint probability density
function f(x, y) = 24xy if 0 < x, 0 < y, and x + y < 1, and zero otherwise.
(a) Find E(XY).
(b) Find the covariance of X and Y.
(c) Find the correlation coefficient of X and Y.
(d) Find Cov(3X, 5Y).
(e) Find Cov(X + 1, Y - 2).
(f) Find Cov(X + 1, 5Y - 2). Ans: https://brainly.com/question/31258251
(g) Find Cov(3X + 5, X).

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables
5.

Ans: E(XY)=1/6,E(Y)=1/2,E(X)=1/4,Var(X)=7/144,Var(Y)=1/12

6. Find Cov(X,Y) from the following data

x 2 8 18 20 28 30
y 5 12 18 23 45 50 Ans:157.83

7. Find Cov(X,Y) from the following data

x 3 4 5 8 7 9 6 2 1
y 4 3 4 7 8 7 6 3 2 Ans:4.8

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Correlation
or
Karl Pearson’s coefficient of correlation

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Introduction

“A correlation is a statistical measure of the relationship between two variables”

The measure is best used in variables that demonstrate a linear relationship

between each other.

The fit of the data can be visually represented in a scatterplot. Using a scatterplot,
we can generally assess the relationship between the variables and determine
whether they are correlated or not.

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Properties of Correlation
1) Correlation coefficient (r) remains in the same measurement as in which the two
variables are.
2) The numerical value of correlation of coefficient will be in between -1 to + 1. It is
known as real number value.
3) The negative value of coefficient suggests that the correlation is strong and
negative. And if ‘r’ goes on approaching toward -1 then it means that the
relationship is going towards the negative side.
When ‘r’ approaches to the side of + 1 then it means the relationship is strong and
positive. By this we can say that if +1 is the result of the correlation then the
relationship is in a positive state

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Formula for Correlation

𝐶𝑜𝑣(𝑋,𝑌)
(OR) 𝑟𝑥𝑦 =
𝜎𝑥 𝜎𝑦

Where:
rxy or simply r – the correlation coefficient of the linear relationship
between the variables x and y
xi – the values of the x-variable in a sample
x̅ – the mean of the values of the x-variable
yi – the values of the y-variable in a sample
ȳ – the mean of the values of the y-variable

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables
Formula-2
When actual mean is not a whole number, but a fraction or when the series is large, the
calculation by direct method will involve a lot of time.
To avoid such tedious calculations, we can use the assumed mean method.

σ 𝑋𝑌
Formula 𝑟𝑥𝑦 =
𝑋2 𝑌2

Where
X is deviation of the items of x – series from an assumed mean i.e., X = x - A
Y is deviation of the items of y – series from an assumed mean i.e., Y = y - A
N is number of items
XY = the total of the product of the deviations of x and y-series from their assumed mean.
X2 = the total of the squares of the deviations of x-series from an assumed mean.
Y2 = the total of the squares of the deviations of y-series from an assumed mean.
X = the total of the deviations of x -series from assumed mean.
Y = the total of the deviations of y -series from assumed mean

∗∗ Note: Notation; rxy = ρxy = ρ(x, y)

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Nature of Correlation

1) If r = Zero this means no association or correlation between the

two variables.

2) If 0 < r < 0.25 = weak correlation.

3) If 0.25 ≤ r < 0.75 = intermediate correlation.

4) If 0.75 ≤ r < 1 = strong correlation.

5) If r = 1 = perfect correlation.

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Calculate coefficient of correlation from the following data:

1) X 12 9 8 10 11 13 7
Y 14 8 6 9 11 12 3 Ans:0.95

2) X 1 2 3 4 5 6 7 Ans:0.79
Y 2 4 5 3 8 6 7

3)

Ans:0.98

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

4)

Ans: E(XY)=1/6,E(Y)=1/2,E(X)=1/4,Var(X)=7/144,Var(Y)=1/12, 𝜌(x, y)=0.6547

5)

Ans: E(XY)=0.2,E(Y)=0.7,E(X)=0.5,Var(X)=0.25,Var(Y)=0.21,𝜌(x, y)=-0.6547

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Partial and Multiple Correlation

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example: Find all Partial and Multiple Correlation for the following

𝑟𝐴𝐵.𝐶 = 0.566
𝑅𝐴.𝐵𝐶 = 0.929

Example
𝑟12.3 = 0.8053, 𝑅1.23 =0.94

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Regression Analysis

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Definition

“Regression analysis is a set of statistical methods used for the

estimation of relationships between a dependent variable and one or
more independent variables”

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Uses of Regression
Regression is a statistical method used in finance, investing, and other disciplines that

attempts to determine the strength and character of the relationship between one

dependent variable (usually denoted by Y) and a series of other variables (known as

independent variables)

-Using the relationship between variables to find the best fit line or the regression

equation that can be used to make predictions.

We have two types of simple linear regressions

1. Linear Regression line Y on X

2. Linear Regression line X on Y

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Linear Regression Y on X
Simple Linear Regression(Regression line Y on X)
Simple linear regression is a model that assesses the relationship between a dependent
variable and an independent variable. The simple linear model is expressed using the
following equation:

Y = a + bX
Where:
Y – Dependent variable
X – Independent (explanatory) variable
a – Intercept
b – Slope
Where a, b are need to be determined with the following normal equations
Y = n a + b X and
XY = a X + b X2

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Linear Regression X on Y
Regression Analysis – Simple Linear Regression(Regression line X on Y)
Simple linear regression is a model that assesses the relationship between a dependent
variable and an independent variable. The simple linear model is expressed using the
following equation:

X = a + bY
Where a, b are need to be determined with the following normal equations
X = n a + b Y and

XY = a Y + b Y2

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Alternative forms of Linear Regressions

ഥ ) = byx (X –𝑿
Linear Regression Y on X: (Y – 𝒀 ഥ)

ഥ ) = bxy (Y –𝒀
Linear Regression X on Y: (X – 𝑿 ഥ)

In this form of regression equation, we need to compute only one

parameter i.e. “b”. This “b” which is also denoted either “byx” or
“bxy” which is called as regression coefficient.

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Methods of finding regression coefficient “byx” or “bxy”

Where N is number of (X,Y) pairs given

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

(H.W)

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example: The regression equations are; 7x - 6y + 9 = 0 and 5y - 4x - 3 = 0. Find

a. The coefficient of correlation (Ans 0.7395)

b. Mean value of x (Ans 0.1034)
c. Mean value of y (Ans.0.5172)

Example: The regression equations are; x=2y+3 and y=kx+6. Find

a. Show that 0≤k≤1/2
b. If k=1/8 then find r and ( ഥ𝑥, ഥ𝑦) ( Ans r=1/2 and (ഥ𝑥, ഥ𝑦) =(20,51/6) )

Dr.E.Prasad
 Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Example

Example Find the means of X and Y variables and the coefficient of correlation between
them from the following two regression equations: 2𝑌−𝑋-50=0 , 3𝑌−2𝑋−10=0

Ans:0.866

Dr.E.Prasad
Probability, Statistics and Reliability Module-3; Bivariate Random Variables

Dr.E.Prasad