0% found this document useful (0 votes)
2 views

Lecture 14 Joint_Probability_Distribution

The document discusses joint probability distributions for both discrete and continuous random variables, explaining how to define their simultaneous behavior through joint probability mass and density functions. It includes examples of calculating joint distributions, marginal distributions, and conditional probabilities, as well as demonstrating statistical independence. The document also provides several examples and solutions to illustrate the concepts presented.

Uploaded by

Mohammad Umar
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
2 views

Lecture 14 Joint_Probability_Distribution

The document discusses joint probability distributions for both discrete and continuous random variables, explaining how to define their simultaneous behavior through joint probability mass and density functions. It includes examples of calculating joint distributions, marginal distributions, and conditional probabilities, as well as demonstrating statistical independence. The document also provides several examples and solutions to illustrate the concepts presented.

Uploaded by

Mohammad Umar
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 30

Joint Probability Distributions

In general, if X and Y are two random


variables, the probability distribution that
defines their simultaneous behavior is
called a joint probability distribution.

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Note:

If X and Y are 2 discrete random variables, this


distribution can be described with a joint
probability mass function. If X and Y are
continuous, this distribution can be described
with a joint probability density function.

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Two Discrete Random Variables:

If X and Y are discrete, with ranges 𝑅𝑋


and 𝑅𝑌 , respectively, the joint
probability mass function is

p(x, y) = P(X = x and Y = y), x ∈ 𝑅𝑋 , y ∈ 𝑅𝑌 .

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
in the discrete case,

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Two Continuous Random Variables:
If X and Y are continuous, the joint
probability density function is a function
f(x,y) that produces probabilities:

𝑃 𝑋, 𝑌 ∈ 𝐴 = ඵ 𝑓 𝑥, 𝑦 𝑑𝑦𝑑𝑥
A

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
in the continuous case,

4) P ( a  x  b ,c  y  d ) =   f (x , y )dydx
bd

ac

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Example:
Suppose we have the following joint mass function
Y -2 0 5
X
1 0.15 K 0.20
3 0.20 0.05 0.15

Find the value of k?

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Answer:
Using
෍ ෍ 𝑓(𝑥, 𝑦) = 1
𝑥 𝑦
We get

0.15 + 0.20 + 𝑘 + 0.05 + 0.20 + 0.15 = 1


0.75 + 𝑘 = 1
𝑘 = 1 − 0.75 = 0.25

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Example:
Suppose we have the following joint density function
6 − x − y
 0x 2 , 2 y 4
f (x , y ) =  8
 0 O .W .

1) Prove that 𝑓(𝑥, 𝑦) is a joint probability function?


2 5
2) Calculate 𝑃 𝑋 ≤ , 𝑌 ≤
3 2

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Answer:
1) f ( x , y )  0
  4 2
6−x − y
  f (x , y ) =   dxdy
− − 2 0 8
14
=   2 ( 6 − x − y ) dx  dy
82  0 
2
14  x2 
=   6x − − yx  dy
82  2 0
1 4  (2) 2  
=   6(2) − − y (2)  − 0  dy
8 2  2  
14
=  (10 − 2 y )dy
82

10 y − y 2  2 = (10(4) − (4) 2 ) − (10(2) − (2) 2 ) 


1 4
=
8
1 1
= ( 40 − 16 ) − ( 20 − 4 ) = ( 8 ) = 1
8 8
503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
2 5
 2 5 6−x − y  3 2
2) P  x  , y   =     dydx
 3 2  0 2 8 

41
= = 0.142 Prove that?
288

Another example see Ex 3.15 on page 96


503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
The marginal distributions

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Example:
Suppose we have the following joint mass function
Y -2 0 5
X
1 0.15 0.25 0.20
3 0.20 0.05 0.15

Find the marginal distributions of X and Y?

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Answer:
Y -2 0 5 Sum
X
1 0.15 0.25 0.20 0.6

3 0.20 0.05 0.15 0.4

Sum 0.35 0.30 0.35 1

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
So
1 3 Sum
x
The marginal distribution
of X f (x ) 0.6 0.4 1

y -2 0 5 Sum

The marginal f ( y ) 0.35 0.30 0.35 1


distribution of Y
15
503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Example:
Suppose we have the following joint density function

f (x , y ) = c ( x + y ) , 0  x 1 , 0  y  2

Find the value of c ?


Find the marginal distributions of X and Y?

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Answer:
 
1)   f ( x , y )dxdy = 1    c ( x + y ) dxdy = 1
2 1

− − 0 0

1 1
c =  f (x , y ) = ( x + y )
3 3
1
( x + y )dy
2
2) f ( x ) =  f ( x , y ) = 
y 0 3

2
 f (x ) = ( x + 1)
3
1
( x + y )dx
1
f ( y ) =  f (x , y ) = 
x 0 3

1 1
 f (y ) =  y + 
3 2
503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
conditional probability distribution

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Example:

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Solution:

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Another example see Ex 3.20 on page 100

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Statistical Independence

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Example:
Suppose we have the following joint distribution

3e e −x −3 y
, x 0, y 0
f (x , y ) = 
 0 , O .W .
Prove that X and Y are independent?

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
f (x , y ) = f (x )  f ( y )
  
1) f (x ) =  f (x , y )dy =  3e e −x −3 y
dy = 3e  e −x −3 y
dy
− 0 0


e 
−3 y

= 3e −x
 −3  = −e −x
 
0 − 1 = e −x
.....................(1)
 0
  
2) f ( y ) =  f (x , y )dx =  3e e −x −3 y
dx = 3e −3 y −x
 dx
e
− 0 0

 −e  0 = −3e −3 y  0 − 1 = 3e −3 y ...............(2)

= 3e −3 y −x

From (1) and (2) 


f (x , y ) = f (x )  f ( y )
503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Notes:
if X and Y are independent, then
1) f (x , y ) = f (x )  f ( y )
2) f ( x y ) = f (x )
3) f ( y x ) = f ( y )

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Example:
Suppose we have the following joint distribution
f (x , y ) = k (8 − x − y ) , 0  x  4 , 1  y  3
Find:
1) The value of k
2) f (x ) , f ( y ) 3) f ( y x ) , f ( x y )
4) P (x  3) 5) P ( x  3 y  2 )

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
Solution:1)    3 4

 f ( x , y )dxdy = 1    k (8 − x − y )dxdy = 1
− − 1 0

 4 3
 k    (8 − x − y )dx dy = 1
1 0

4
 3
x  2

 k  8x − − xy  = 1
1 2 0
 3
42 
 k  8(4) − − 4y dy = 1
1 2 
3
 k  ( −4 y + 24 )dy = 1
1

3
 −4 y 2

k  + 24 y  = 1
 2 1
1 1
 k ( 32 ) = 1  k =  f ( x , y ) = (8 − x − y )
32 32
503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili

2) f ( x ) =  f ( x , y )dy
−

1 3
 f (x ) =  ( 8 − x − y ) dy
1 32

1
 f (x ) = (12 − 2x ) , 0x 4
32

f ( y ) =  f ( x , y )dx
−

1 4
 f (y ) =  ( 8 − x − y ) dx
0 32

1
 f (y ) = ( 24 − 4 y ) , 1 y  3
32
503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
1
f (x , y ) 32 ( 8−x − y )
( 8−x − y )
3) f ( y x ) = = =
f (x ) 1
(12 − 2 x ) (12 − 2 x )
32

1
f (x , y ) 32 ( 8−x − y )
( 8−x − y )
f (x y ) = = =
f (y ) 1
( 24 − 4 y ) ( 24 − 4 y )
32

3
27
4) P (x  3) =  f (x )dx =
0 32
503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili
P (x  3, y  2)
5) P ( x  3 y  2 ) =
p ( y  2)

23
1 30
23
P (x  3, y  2) =   f (x , y )dxdy =   ( 8 − x − y ) dxdy =
10 1 0 32 64
2
1 2
18
p ( y  2) =  f ( y )dy =  ( 24 − 4 y ) dy =
1 1 32 32

5
P ( x  3 y  2) =
6

503 STAT - Probability and Statistics for Engineers and Scientists – Dr. Mansour Shrahili

You might also like