1

Jointly distributed Random

variables

Multivariate distributions
 2

Jointly distributed Random

variables

Multivariate distributions

2 or more random variables (X, Y, etc)

defined for the same random
experiment.
 3
(introduction)Example for illustration
• Toss a coin 3 times. Define,
X: total number of tails,
Y: total number of heads.
• The sample space is S ={TTT, TTH, THT, HTT, THH,
HTH, HHT, HHH}.
• We display the joint probability distribution of X and Y
in the following table : f  x, y   P  X  x and Y  y 
y 0 1 2 3

x
0 0 0 0 p(HHH)=1/8
1 0 0 p(HTH, ,THH,HHT)=3/8 0
2 0 P(TTH, HTT,THT)=3/8 0 0
3 P(TTT)=1/8 0 0 0 3
 4

General properties of the joint probability

function; Discrete case
f(x,y) = P[X = x, Y = y]

1. 0  f  x, y   1

2.  f  x, y   1
x y

3. P  X , Y   A   f  x, y 
 x, y   A
 5

Example:
Two dice are rolled
Sample space:

X = the number of times a “six” appears.

Y = the sum of values of the two dice number.
 6

Table: f (x,y) (joint probability distribution)

y 2 3 4 5 6 7 8 9 10 11 12
x
0 1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0

1 0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0

2 0 0 0 0 0 0 0 0 0 0 1/36

what is P(X  1, Y  4)

1 2  3
P(X  1, Y  4)   f  x, y  
36
1 2 1 4
what is P[Y=X +10]? P Y  X  10  
36 36
 7

Marginal and conditional

distributions
 8
Definition:
Let X and Y denote two discrete random variables
with joint probability function
f(x,y) = P[X = x, Y = y]
Then
fX(x) = P[X = x] is called the marginal probability
function of X.
and
fY(y) = P[Y = y] is called the marginal probability
function of Y.
 9
Note: Let y1, y2, y3, … denote the possible values of Y.

f X  x   P  X  x    f  x, y j    f  x, y 
j y

Thus the marginal probability function of X, fX(x) is

obtained from the joint probability function of X and Y by
summing f(x,y) over the possible values of Y.
 10
Also
fY  y   P Y  y    f  xi , y    f  x, y 
i x

Thus the marginal probability function of y, fY(y) is

obtained from the joint probability function of X and Y by
summing f(x,y) over the possible values of X.
 11

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12
x
0 1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0

1 0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0

2 0 0 0 0 0 0 0 0 0 0 1/36
 12

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
1 0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0

2 0 0 0 0 0 0 0 0 0 0 1/36
 13

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36
1
2 0 0 0 0 0 0 0 0 0 0 1/36
 14

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36
1
0 0 0 0 0 0 0 0 0 0 1/36 1/36
2
 15

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36
1
0 0 0 0 0 0 0 0 0 0 1/36 1/36
2
fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

25 10 fY ( y  7)  6
f X ( x  0)  f X ( x  1) 
36 36 36
 16

Conditional Distributions
 17
Definition:
Let X and Y denote two discrete random variables
with joint probability function
f(x,y) = P[X = x, Y = y]
Then
fX |Y (x)= P[X = x|Y = y] is called the conditional probability
function of X given Y = y

and
fY |X (y)= P[Y = y|X = x] is called the conditional probability
function of Y given X = x
 18
Note
f X Y ( x)  P  X  x Y  y 
P  X  x, Y  y  f  x , y 
 
P Y  y  fY  y 
and
fY X ( y )  P Y  y X  x 

P  X  x, Y  y  f  x, y 
 
P  X  x fX  x
 19
Difference between Marginal distributions
and Conditional Distributions

• Marginal distributions describe how one

variable behaves ignoring the other variable.

• Conditional distributions describe how one

variable behaves when the other variable is
held fixed
 20
Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.

y 2 3 4 5 6 7 8 9 10 11 12
x f X ( x)
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36
1
0 0 0 0 0 0 0 0 0 0 1/36 1/36
2
fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

p  x  0 y  7 
 21
Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.

y 2 3 4 5 6 7 8 9 10 11 12
x f X ( x)
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36
1
0 0 0 0 0 0 0 0 0 0 1/36 1/36
2
fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

4
 0, 7 
p  x  0 y  7 
f 36  2

fY  y  7  6 3
36
 22

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36
1
0 0 0 0 0 0 0 0 0 0 1/36 1/36
2
fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

p  y  3 x  0
 23

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36
1
0 0 0 0 0 0 0 0 0 0 1/36 1/36
2
fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

2
f  0, 3
p  y  3 x  0 36 2
  
f X  X  0 25 25
36
 24

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36
1
0 0 0 0 0 0 0 0 0 0 1/36 1/36
2
fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

p  y  9 x  1
 25

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36
1
0 0 0 0 0 0 0 0 0 0 1/36 1/36
2
fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

p  y  9 x  1
 26

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36
0
0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36
1
0 0 0 0 0 0 0 0 0 0 1/36 1/36
2
fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

6
p  y  9 x  1  f  x  1, y  9   36 
6
fX X  1 11 11
36
 27

Mean and Variance

• If the marginal probability distribution of X
has the probability function f X ( x) , then

E ( X )   X   xf X ( x)
x

V ( X )   2 X   ( x   X ) 2 f X ( x)
x

 2 X  E( X 2 )   2 X
 28

Mean and Variance

• Similarly
E (Y )  Y   yfY ( y )
y

 2Y  E(Y 2 )   2Y

E ( XY )   XY   xyf ( x, y )
y x

cov( X , Y )   XY  E ( XY )   X Y
 29

Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
0 1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36

1 0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36

2 0 0 0 0 0 0 0 0 0 0 1/36 1/36

fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

25 10 1 1
 X   xf X ( x)  0   1  2 
x 36 36 36 3
1 2 3 1
Y  2   3   4   ..............  12   7
36 36 36 36 114
 XY   xyf ( x, y )   3.16
y x 36
 30
Example:
Two dice are rolled
X = the number of times a “six” appears.
Y = the sum of values of the two dice number.
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
0 1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36

1 0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36

2 0 0 0 0 0 0 0 0 0 0 1/36 1/36

fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36
2
25 10 1 1 10
 2X 0 
2
1 
2
2 
2
  
36 36 36  3  36
1 2 1
 2Y  2 2   32   ...........12 2    7   5.83
2

36 36 36
1
cov( X , Y )  E ( XY )   X Y  3.16  ( )7  0.8266
3
 31

Independence
• For discrete random variables X and Y, are
f  x, y 
independent if .
fY X ( y )   fY ( y )
fX  x

f  x, y   fY ( y ) f X  x  for all x and y

.

• If we find one pair of x and y in which the

equality fails, X and Y are not independent.
 32

Independence
Example: check whethere X and Y are independent or not

y 2 3 5
f X ( x)
x

0 0.36 0.18 0.06 0.6

1 0.24 0.12 0.04 0.4
fY ( y )
0.6 0.3 0.1
X ,Y are independent
 33

Correlation
 34
Example:
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
0 1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36

1 0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36

2 0 0 0 0 0 0 0 0 0 0 1/36 1/36

fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

10
 2X   2Y  5.83 cov( X , Y )  0.8266
36

Evaluate  XY
0.8266
cov(X ,Y )  XY   0.6495
XY  10
V (X )V (Y) ( )(5.83)
36
 35

Linear Combinations of Random

Variables
Mean of a Linear Combination

E (c1 X  c2Y )  c1E ( X )  c2 E (Y )

Variance of a Linear Combination

V (c1 X  c2Y )  c12V ( X )  c 22V (Y )  2c1c2 cov( X , Y )

 36
Example:
y 2 3 4 5 6 7 8 9 10 11 12 f X ( x)
x
0 1/36 2/36 3/36 4/36 5/36 4/36 3/36 2/36 1/36 0 0 25/36

1 0 0 0 0 0 2/36 2/36 2/36 2/36 2/36 0 10/36

2 0 0 0 0 0 0 0 0 0 0 1/36 1/36

fY ( y ) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

X 
1
Y  7  XY  3.16
3
10
 2X   2Y  5.83 cov( X , Y )  0.8266
36
Evaluate E (2 X  3Y ) V (2 X  3Y )
1
E (2 X  3Y )  2 E ( X )  3E (Y )  2    3  7   21.666
3
 10 
V (2 X  3Y )  4V ( X )  9V (Y )  12cov( X , Y )  4    9 5.83  12  0.8266   63.5
 36 
 37

Summary
Discrete Random Variables
1. 0  f  x, y   1

2.  f  x, y   1
x y

3. P  X , Y   A   f  x, y 
 x, y   A
 38

Summary
Discrete Random Variables
f  x, y 
f X Y ( x) 
fY  y 

f  x, y 
fY X ( y ) 
fX  x

For independent random vriables

f  x, y   fY ( y ) f X  x 
 39

Summary
Discrete Random Variables
 X   xf X ( x)  2 X  E( X 2 )   2 X
x

Y   yfY ( y )  2Y  E(Y 2 )   2Y
y

 XY   xyf ( x, y )  XY  E ( XY )   X Y
y x

E (c1 X  c2Y )  c1E ( X )  c2 E (Y )

V (c1 X  c2Y )  c12V ( X )  c 22V (Y )  2c1c2 cov( X , Y )

 40

Summary
Discrete Random Variables

Correlation
 41

Example
• Suppose we roll a fair die then we toss a fair coin .
Let X = number of heads, Y = number on die.
• the joint probability distribution of X and Y in the
following table :
y 1 2 3 4 5 6

0 1/12 1/12 1/12 1/12 1/12 1/12

1 1/12 1/12 1/12 1/12 1/12 1/12

4 2
P(X=0, Y  4)  P Y  3  X  
12 12

11
P X  Y  
12
 42

Example
• Suppose we roll a fair die then we toss a fair coin .
Let X = number of heads, Y = number on die.
y 1 2 3 4 5 6
f X ( x)
x
0 1/12 1/12 1/12 1/12 1/12 1/12 0.5

1 1/12 1/12 1/12 1/12 1/12 1/12 0.5

fY ( y ) 1/6 1/6 1/6 1/6 1/6 1/6

f X ( x  0)  0.5 fY ( y  5) 
1
6
4
f X ( x  1)  0.5 fY  y  3  
6
 43

Example
• Suppose we roll a fair die then we toss a fair coin .
Let X = number of heads, Y = number on die.
y 1 2 3 4 5 6
f X ( x)
x
0 1/12 1/12 1/12 1/12 1/12 1/12 0.5

1 1/12 1/12 1/12 1/12 1/12 1/12 0.5

fY ( y ) 1/6 1/6 1/6 1/6 1/6 1/6

1
 0, 4 
p  x  0 y  4
f 1
  12 
fY  y  4 1 2
6
1
 0, 3
p  y  3 x  0
f 2
  12 
fX  X  0 0.5 12
4
f x  1, y  3 
p  x  1 y  3 
1
 12 
fY y  3 4 2
6
 44

Example
• Suppose we roll a fair die then we toss a fair coin .
Let X = number of heads, Y = number on die.
y 1 2 3 4 5 6
f X ( x)
x
0 1/12 1/12 1/12 1/12 1/12 1/12 0.5

1 1/12 1/12 1/12 1/12 1/12 1/12 0.5

fY ( y ) 1/6 1/6 1/6 1/6 1/6 1/6

 X   xf X ( x)  0  0.5  1 0.5  0.5

x

1 1 1 1 21
Y  1  2   3   ..............  6  
6 6 6 6 6

1 1 1 1 21
 XY   xyf ( x, y)  1  2   3   ..............  6  
y x 12 12 12 12 12
 45

Example
• Suppose we roll a fair die then we toss a fair coin .
Let X = number of heads, Y = number on die.
y 1 2 3 4 5 6
f X ( x)
x
0 1/12 1/12 1/12 1/12 1/12 1/12 0.5

1 1/12 1/12 1/12 1/12 1/12 1/12 0.5

fY ( y ) 1/6 1/6 1/6 1/6 1/6 1/6

2
 2 X  02  0.5  12  0.5   1   0.25
2
2
1 2 1 2 1 1  21 
 2Y  1   2   3   ..............  6      2.91
2 2

6 6 6 6 6

cov( X , Y )  E ( XY )   X Y  21  (0.5) 21  0
12 6
 46

Example
• Suppose we roll a fair die then we toss a fair coin .
Let X = number of heads, Y = number on die.
y 1 2 3 4 5 6
f X ( x)
x
0 1/12 1/12 1/12 1/12 1/12 1/12 0.5

1 1/12 1/12 1/12 1/12 1/12 1/12 0.5

fY ( y ) 1/6 1/6 1/6 1/6 1/6 1/6

 2 X  0.25  2Y  2.91 cov( X , Y )  0

cov( X , Y ) 0
 XY   XY  0
V ( X )V ( X ) (0.25)(2.91)
 47

Example
• Suppose we roll a fair die then we toss a fair coin .
Let X = number of heads, Y = number on die.
y 1 2 3 4 5 6
f X ( x)
x
0 1/12 1/12 1/12 1/12 1/12 1/12 0.5

1 1/12 1/12 1/12 1/12 1/12 1/12 0.5

fY ( y ) 1/6 1/6 1/6 1/6 1/6 1/6

1 21
X  Y  3.5 X Y   2 X  0.25  2Y  2.91 cov( X , Y )  0
2 12

Evaluate V (X Y )
E ( X  2Y )
1
E (X  2Y )  E (X )  2E (Y )     2  3.5 
2
V (X Y ) V (X ) V (Y )  2cov(X ,Y )   0.25    2.91  2  0  
 48

Example
• Suppose we roll a fair die then we toss a fair coin .
Let X = number of heads, Y = number on die.
y 1 2 3 4 5 6
f X ( x)
x
0 1/12 1/12 1/12 1/12 1/12 1/12 0.5

1 1/12 1/12 1/12 1/12 1/12 1/12 0.5

fY ( y ) 1/6 1/6 1/6 1/6 1/6 1/6

check whethere X and Y are independent or

dependent

X ,Y are independent
 49

Example
• Let X -2 -1 1 2
if Y  X 2
f(x) 0.2 0.3 0.35 0.15
• Compute
f ( x, y ),  ( X , Y )
X -2 -1 1 2

Y
 50

Example
• Let X -2 -1 1 2
if Y  X 2
f(x) 0.2 0.3 0.35 0.15
• Compute
f ( x, y )
X -2 -1 1 2

1
 51

Example
• Let X -2 -1 1 2
if Y  X 2
f(x) 0.2 0.3 0.35 0.15
• Compute
f ( x, y )
X -2 -1 1 2

4 0.2 0 0 0.15

1 0 0.3 0.35

Continue.
52
 53

Continuous Random Variables

Definition: Two random variable are said to have
joint probability density function f(x,y) if

1. 0  f  x, y 
 
2.   f  x, y  dxdy  1
 

3. P  X , Y   A    f  x, y  dxdy

A
If 0  f  x, y  then z  f  x, y 
defines a surface over the x – y plane

  f  x, y  dxdy
A
Multiple Integration
 A  f  x, y  dxdy

f(x,y)
If the region A = {(x,y)| a ≤ x ≤ b, c ≤ y ≤ d} is a
rectangular region with sides parallel to the
coordinate axes:
y
d

Then a b x

  f  x, y  dxdyd
 b
 b
 d

    f  x, y  dx  dy     f  x, y  dy  dx
A

c  a  a  c 
To evaluate
d b

  f  x, y  dxdy    f  x, y  dxdy
c a
A

d b

    f  x, y  dx  dy
c a 
First evaluate the inner integral
b
G  y    f  x, y  dx
a

Then evaluate the outer integral

d b d

  f  x, y  dxdy   G  y  dy
c a c
The same quantity can be calculated by integrating
first with respect to y, than x.
b d

  f  x, y  dxdy    f  x, y  dydx
a c
A

b d

    f  x, y  dy  dx
a c 
First evaluate the inner integral
d
H  x    f  x, y  dy
c

Then evaluate the outer integral

b d b

  f  x, y  dydx   H  x  dx
a c a
Example: Compute
1 1 1 1

 x y  xy  dxdy     x y  xy  dydx

2 3 2 3

0 0 0 0
Now
1 1 1
 1

0 0  x y  xy  dxdy  0  0  x y  xy  dx  dy
2 3 2 3

1  3
x 3 
2 x 1
x
  y y  dy
0 x 0 
3 2
 
4 y 1
1 1 3
1 2
1y 1y
   y  y  dy  
0
3 2  3 2 2 4 y 0
1 1 7
  
6 8 24
The same quantity can be computed by reversing
the order of integration
1 1 1
 1

0 0  x y  xy  dydx  0  0  x y  xy  dy  dx
2 3 2 3

 y2
1
y 4 y 1

  x 2
x  dx
0
2 4 y 0 
 

2 x 1
1 2 1 
1 3
1x 1x
   x  x  dx  
0
2 4  2 3 4 2 x 0
1 1 7
  
6 8 24
Integration over non rectangular
regions
If the region A is defined as follows
A = {(x,y)| a ≤ x ≤ b, h(x) ≤ y ≤ g(x) }
y y=g(x)

y=h(x)
Then a b x
b y g x 
A f  x, y  dxdy     f  x, y  dy  dx
a y  h x  
Suppose the region A is defined as follows
A = {(x,y)| h(y) ≤ x ≤ g(y), c ≤ y ≤ d}
y
d

x=h(y) x=g(y)
c

Then x
d  x g  y  
A f  x, y  dxdy     f  x, y  dx  dy
c 
 x  h y  
Example:
Compute the volume under f(x,y) = x2y + xy3 over the
region A = {(x,y)| x + y ≤ 1, 0 ≤ x, 0 ≤ y}
y

(0, 1)

x+y=1

(1, 0)

x
Now integrating first with respect to y then x
y

(0, 1) x+y=1

(y=1 – x )

(1, 0)

(y= 0) x
1 1 x

    dydx      dydx
2 3 2 3
x y xy x y xy
0 0
A
1
1 x 2 
     x y  xy  dy  dx
3

0 0 
Hence
1

1 x
   y 2
y
14

y 1 x

0  0  x y  xy  dy  dx   2  x 4   dx
2 3
  x 2

 0
 y 0 

1  x  1 x
1 2 4

x 2
x dx
0
2 4
x 2  2 x3  x 4 x  4 x 2  6 x3  4 x 4  x5
1
  dx
0
2 4
x  2 x 2  2 x3  2 x 4  x5
1
 dx
0
4
 18  16  18  101  201  15 20120
1512 6
 120
4
Integrating first with respect to x then y
y

(0, 1) x+y=1

(x=0) (x=1 – y)

(1, 0)

x
1 1 y

    dxdy      dxdy
2 3 2 3
x y xy x y xy
A 0 0


1 1 y

     x y  xy  dx  dy
2 3

0 
0 
and
1

1 y
  1 x 1 y

0  0      3 y  2 y  dy
3 2
x x
x 2
y  xy 3
dx dy  3

  0  x 0  
1 
1 y 1 y 3 
3 2

  y y  dy
0 
3 2

1
 y  3 y 2  3 y3  y 4 y3  2 y 4  y5 
    dy
0  
3 2

 1  43  15 14  52  16
1
 2

3 2
 16  13  14  151  18  15  121
 20  40  30 815 24 10
120  120
3
 1
40
Continuous Random Variables
Definition: Two random variable are said to have
joint probability density function f(x,y) if

1. 0  f  x, y 
 
2.   f  x, y  dxdy  1
 

3. P  X , Y   A    f  x, y  dxdy

A
Definition: Let X and Y denote two random
variables with joint probability density function
f(x,y) then
the marginal density of X is

f X  x    f  x, y  dy

the marginal density of Y is

fY  y    f  x, y  dx
 Example
• Consider the following density function

6 xy 2
0  x  1, 0  y  1
f  x, y   
 0 otherwise
• Check if it is a valid density function.
 1 1

 
1 1

0 0  6xy 2
 dxdy     6xy 2
dx  dy
0 0 
1

 
1
3 y 1
3 x 2 y 2 x 1  dy   3 y dy  y 1
0 
2
x 0 
 y 0
0
 Example
• Consider the following density function

6 xy 2
0  x  1, 0  y  1
f  x, y   
 0 otherwise
• Compute P(X ≤ 1 ,Y ≤ ½ ).
1 1
 1

 
2 1 2

  
6xy 2 dxdy     6xy dx  dy
2

0 0 0 0 
1 1
1

 
2
2  1
3 x y  dy  3 y dy  y

y
2 x 1 
0 
2 2 3 2
x 0 
 y 0 8
0
 Example
Compute P(X ≤ Y ).
y

(0, 1) y=1
 y 1
1 
 
    6 xy dy  dx
2

0 
 yx 
y=x
(1, 0)
x
1
 2 xy
1 1

 dx   2 x  2 x 4  dx  x 2 
3 y 1 2 x 5
 3
0  y  x  0   0  5 
 dx 
5
 Example
• Consider the following density function

6 xy
2
0  x  1, 0  y  1
f  x, y   
 0 otherwise
• Find the marginal densities of X and Y.
1 1
f X  x    f  x, y  dy    6 xy  dy  2 xy
2 3 y 1
 2x
y 0
0 0

1 1
fY  y    f  x, y  dx    6 xy  dx  3x y
2 2 2 x 1
 3y 2
x 0
0 0
 Example(conditional prob )
• Consider the following density function

6 xy
2
0  x  1, 0  y  1
f  x, y   
 0 otherwise
1 1
Compute p( X 
Y  )
4 2
1 1
p( X  , Y  )
1 1 4 2
p( X  Y  ) 
4 2 1
p (Y  )
2
 0.25
0.5

  
  6 xy dx  dy
2

p( X  Y  )  00.5 10 
1 1
 
 
4 2
0  0 6 xy dx  dy
2
Definition: Let X and Y denote two random
variables with joint probability density function
f(x,y) and marginal densities fX(x), fY(y) then
the conditional density of Y given X =x
f  x, y 
fY X  y  
fX  x

conditional density of X given Y = y

f  x, y 
fX Y  x 
fY  y 
 Proof)‫(االثبات غير مطلوب‬
p(c  Y  d X  a)  lim p(c  Y  d a  X  a  h)
h 0

p (c  Y  d , a  X  a  h )
p(c  Y  d X  a )  lim
h 0 p ( a  X  a  h)
ah
d 
    f ( x, y  dy  dx
p (c  Y  d X  a )  lim a c  
0
h 0 ah
0
  f X  x  dx
Use L’Hospital rule a

d
ah
d 
    f ( x, y  dy  dx
dh c 
p (c  Y  d X  a )  lim a
ah
h 0 d
dh   f X  x 
  dx
a
 Proof
d

  f (a  h, y  dy
p (c  Y  d X  a )  lim c
h 0 f X a  h
d

  f (a, y  dy
p (c  Y  d X  a )  c
fX a
Conditional

p (c  Y  d X  a)  
 f ( a, y 
d
dy
density

c
fX a

p (c  Y  d X  x)  
 f ( x, y 
d
dy
c
fX  x
Definition: Let X and Y denote two random
variables with joint probability density function
f(x,y) and marginal densities fX(x), fY(y) then
the conditional density of Y given X =x
f  x, y 
fY X  y  
fX  x

conditional density of X given Y = y

f  x, y 
fX Y  x 
fY  y 
 Example
• Consider the following density function
10 xy 2 0  x  y 1
f  x, y   
 0 otherwise
Compute p( y  0.5 x  0.75) y
(0, 1) y=1 (1, 1)
1
10
f X  x    10 xy dy  x(1  x 3 )
2

x
3
10 xy 2 3y2
fY X  y  
y=x

x(1  x 3 ) (1  x )
3
10
x
3
1 1 2
3y
p( y  0.5 x  0.75)   fY X 0.75  y  dy   dy
0.75 0.75
(1  (0.75) )
3
 Example
• Consider the following density function
10 xy 2 0  x  y 1
f  x, y   
 0 otherwise
Compute p( y  0.5 x  0.25) y
(0, 1) y=1 (1, 1)
1
10
f X  x    10 xy dy  x(1  x 3 )
2

x
3
10 xy 2 3y2
fY X  y  
y=x

x(1  x 3 ) (1  x )
3
10
x
3
1 1 2
3y 8
p( y  0.5 x  0.25)   fY X 0.25  y  dy   dy 
0.5 0.5
(1  (0.25) )
3
9
 Mean and variance
 X   xf x ( x)dx    xf  x, y  dxdy

Y   yfY ( y)dy    yf  x, y  dxdy

 XY    xyf  x, y  dxdy

 X 2   x2 f ( x, y)dxdy   2 X
R

 Y 2   y 2 f ( x, y)dxdy   2Y
R

cov( x, y)   XY   xy f ( x, y)dxdy   X Y
R
 Example
• Consider the following density function
10 xy 2 0  x  y 1
f  x, y   
 0 otherwise
Evaluate  X , X 2 ,cov( X , Y ) y
(0, 1) y=1 (1, 1)
1 1
10 2 3
1 y 1
 5
 X    x(10 xy )dydx    x y
2
 dx 
0 
3 yx 
0 x  9
1 1 y=x
 X    x (10 xy )dydx  
2 2 2 2
X  0.0485
0 x
x
1 1
cov( x, y )   XY    xy (10 xy 2 )dydx   X Y  0.01322
0 x
 Linear Combinations of Random
Variables
Mean of a Linear Combination

E (c1 X  c2Y )  c1E ( X )  c2 E (Y )

Variance of a Linear Combination

V (c1 X  c2Y )  c12V ( X )  c 22V (Y )  2c1c2 cov( X , Y )

 Example
• Consider the following density function
10 xy 2 0  x  y 1
f  x, y   
 0 otherwise
Evaluate E ( X  Y ), var( X  Y ) y
(0, 1) y=1 (1, 1)
1 1

1
10
y 1
 5
E ( X )    x(10 xy )dydx    x y
2 2 3
 dx 
0 
3 yx 
0 x  9
1 1 1
 10 4 
y 1
5
E (Y )    y (10 xy )dydx    xy
2
 dx  y=x
0 
4 yx 
0 x  6
x
E ( X  Y )  E ( X )  E (Y )
5 5
E( X  Y )  
9 6
 Example
• Consider the following density function
10 xy 2 0  x  y 1
f  x, y   
 0 otherwise
Evaluate E ( X  Y ), var( X  Y ) y
(0, 1) y=1 (1, 1)
1 1
 X 2    x 2 (10 xy 2 )dydx   2 X  0.0485
0 x
1 1
 Y 2    y 2 (10 xy 2 )dydx   2Y  0.0198 y=x
0 x
1 1
cov( x, y )   XY    xy (10 xy 2 )dydx   X Y  0.01322 x
0 x

V ( X  Y )  V ( X )  V (Y )  2 cov( X , Y )
V ( X  Y )  0.0485  0.0198  2(0.01322)  0.09474
Correlation
 Example
• Consider the following density function
10 xy 2 0  x  y 1
f  x, y   
 0 otherwise
Evaluate  XY y
(0, 1) y=1 (1, 1)
cov( X , Y )
 XY 
V ( X )V (Y )

0.01322 y=x
 XY   0.4266
(0.0485)(0.0198)
x
 Example(conditional prob )
• Consider the following density function
 2 xy
x  0  x  1, 0  y  2
f  x, y    3
 0 otherwise
Find
p  x  1/ 2 y  1/ 2 
p  x  1 / 2, y  1 / 2 
p  x  1 / 2 y  1 / 2 
p  y  1 / 2
1  y 2  2 xy   43
p  x  1 / 2, y  1 / 2      x   dy  dx 
 y 1/ 2 
1/ 2 
3  
 64

1  y 2  2 xy   13
p  y  1 / 2    x   dy  dx 
 y 1/ 2 
0 
3  
 16
43
p  x  1 / 2, y  1 / 2 
p  x  1 / 2 y  1 / 2 
43
 64 
p  y  1 / 2 13 52
16