CONDITIONAL EXPECTATIONS

Conditional expectations of random are defined in terms of their conditional

distributions.
Definition 4
If X and Y are discrete random variables and f (x / y ) is the value of the conditional
probability distribution of X given Y = y at x, the conditional expectation of u( X )
given Y = y is
u( X )
E [ y ]
=∑ u ( x )⋅f ( x / y )
x

Correspondingly, if X and Y are continuous random variables and f (x / y ) is the

value of the conditional probability density of X given Y = y at x, the conditional
expectation of u( X ) given Y = y is
u( X )
E [ y ]∫
= u (x )⋅f ( x / y )dx
x

Similar expressions based on the conditional distribution or density of Y given X = x

define the conditional expectation of v (Y) given X = x.

If we let u( X )=X in Definition 4, we obtain the conditional mean of the random

variable X given Y = y, which we denote by
μ X / Y = y=E [ X Y=y]
Correspondingly, the conditional variance of the random variable X given Y = y, is
2
2
[
σ X / Y = y =E ( X − μ X / y ) / y =E
2
] [ X
Y= y ] 2
−μ X / y

where
E [ X
Y=y ] is given by Definition 4 with u( X )=X
2
.

Example 22
With reference to Example 1, find the conditional mean of X given Y = 1.
Solution
Making use of the results obtained in Example 10, that is
4 3
f (0/1)= , f (1/1)= , f (2/1)=0
7 7 , we get
X
E [ Y =1 ]
=∑ x⋅f ( x / Y =1)
x
4 3 3
= 0⋅ +1⋅ + 2⋅0=
7 7 7

Page 1 of 6
Example 23
If the joint probability density of X and Y is given by
2
3 {
f (x , y)=¿ ( x+2 y ) for 0<x<1, 0<y<1 ¿ ¿¿¿
1
Y=
Find the conditional mean and the conditional variance of X given 2 .
Solution
Performing the necessary integrations, we get
1 1
2 2 2
[ xy + y 2 ] y =0= 2 [ x +1 ]
1
g ( x ) =∫ f ( x , y ) dy= ∫ ( x+2 y ) dy= ∫ ( x+2 y ) dy=
y y=0 3 3 y=0 3 3

2
i.e.
3 {
g ( x ) =¿ ( x+1) , 0<x<1 ¿ ¿¿¿
Also
1 1 1
2 2 2 x2
h ( y )=∫ f ( x , y ) dx= ∫ ( x+2 y ) dx=
x x =0 3 3
∫
x=0
( x +2 y ) dx=
3 2[ +2 xy ] x =0
2 1 1
=
3 2 [ ]
+2 y = ( 1+4 y )
3
1
i.e.
3 {
h ( y )=¿ ( 1+4 y ) , 0<y<1 ¿ ¿¿¿
Then, substituting into the formula for a conditional density, we get
2
( x +2 y )
x f (x , y) 3 2 x+ 4 y
f ( )
y
=
h( y)
=
1
( 1+4 y )
=
1+ 4 y
3

x 2x+4 y
i.e.,
f ( y) { =¿
1+4 y
, 0<x<1 ¿ ¿¿¿
so that

x 2
f
( ) Y=
1
=¿ { 3
( x+1 ) , 0<x<1 ¿ ¿¿¿
2

μX
Thus, Y =1/2 is given by

Page 2 of 6
 1 1
X 2 2
μX
Y =1/2
=E ( ) 2
= ∫ x⋅ ( x +1)dx = ∫ ( x +x )dx
Y =1/2 x=0 3 3 x=0
1
2 x3 x2 2 1 1 5
= +
3 3 2[ ] [ ] x =0
= + =
3 3 2 9
Next we find
1 1
X2 2 2
μX 2

Y=1/2
=E ( ) 2 3 2
= ∫ x ¿ ( x +1)dx = ∫ ( x +x )dx
Y =1/2 x=0 3 3 x=0
1
2 x 4 x3 2 1 1 7
=
3 4 3[ ] [ ]
+
x=0
= + =
3 4 3 18
and it follows that

7 5 2 13
2
σX = −
Y=1/2
=
18 9 162 ()
EXERCISES
1
f (x , y )=
1. If X and Y have the joint probability distribution for x = -3 and y = 4
-5, x = -1 and y = -1, x = 1 and y = 1, and x = 3 and y = 5, find cov( X , Y ) . ⇒ [ 8 ]
2. Given the values of the joint probability distribution of X and Y shown in the
table:

x
0 1 2
0 1 1 1
12 6 24
y 1 1 1 1
4 4 40
2 1 1 0
8 20
3 1 0 0
120

Find the covariance and the correlation coefficient of X and Y.

3. If X and Y have the joint probability distribution
1 1 1 1
f (−1,0 )=0 , f (−1,1)= 4 , f (0,0)= 6 , f (0,1)=0 , f (1,0 )= 12 , and f (1,1)= 2 , show that:
(a) cov ( X , Y )=0 .
The two random variables are not independent
(b)
4. The joint cumulative density function of two random variables X and Y is given
by:

Page 3 of 6
 −x2 − y2
{
F(x,y)=¿ (1−e ) ( 1−e ) for x>0, y>0 ¿ ¿¿¿
Find:
(a) The joint probability density function of the two random variables X and
Y.
−1 −4 2
(b) Pr ( 1< X≤2,1<Y ≤2 ) . ⇒ ( e −e ) =0 . 1222
(c) The covariance and the correlation coefficient of X and Y.

5. For k random variables

X 1 , X 2 ,⋯, X k , the values of their joint moment-
generating function are given by;
t x1+t 2 x2+⋯+t k xk
E (e 1 )
(a) Show for either the discrete case or the continuous case that the partial

derivative of the joint moment-generating function with respect to

ti at
t1 =t 2 =⋯=t k =0 is i . E( X )
(b) Show for either the discrete case or the continuous case that the second
partial derivative of the joint moment-generating function with respect to
ti and t j , i≠ j
at 1 2 k t =t =⋯=t =0
is i j . E( X X )
(c) If two random variables have the joint probability density given by:

f (x,y)=¿ {e−x−y for x>0, y>0 ¿ ¿¿¿

Find theirjoint moment-generating function and use it to determine the
values of E( XY ), E( X ), E(Y ), and cov ( X , Y )
1
[
⇒ E (e 1
t X +t 2 Y
)=
(1−t 1 )(1−t2 )
, E( XY )=1 , E ( X )=1 , E (Y )=1 , and cov ( X , Y )=0
]
6. If
X , X , and X
1 2 3 are independent and have the means 4, 9, and 3 and the
variances 3, 7, and 5, find the mean and the variance of:

(a)
Y=2 X 1 −3 X 2 +4 X 3 ;

(b) 1 Z=X +2 X − X
2 3
7. Repeat both parts of Exercise 6, dropping the assumption of independence and
using instead the information that
cov( X 1 , X 2 )=1, cov( X 2 , X 3 )=−2, and cov( X 1 , X 3 )=−3 . [(a) 143; (b) 54]
8. If the joint probability density of X and Y is given by
1
{
f (x , y)=¿ ( x+ y ) for 0<x<1, 0<y<2 ¿ ¿¿¿
3

Page 4 of 6
 Find the variance of W=3 X +4 Y −5 .

9. If
var( X 1 )=5, var( X 2)=4 , var( X 3 )=7 , cov( X 1 , X 2 )=3, cov( X 1 , X 3 )=−2 , and
X 2 and X 3 are independent, find the covariance of
Y 1 =X 1−2 X 2+3 X 3 and
Y 2=−2 X 1 +3 X 2+4 X 3
. [75]
10. With reference to Exercise 6, find cov (Y , Z ) .
11. Given the values of the joint probability distribution of X and Y shown in the
table:
x
-1 1
-1 1 1
8 2
y 0 0 1
4
1 1 0
8
Find the conditional mean and the conditional variance of X given Y = -1.
3 16
[ ⇒ μX
Y =−1
2
= , and σ X =
5 Y=−1 25 ]
12. If the joint probability density of X and Y is given by:

f ( x , y ) =¿ 14 ( 2 x+y ) for 0<x<1, 0<y<2 ¿ ¿¿¿

{ 1
Find theconditional mean and the conditional variance of Y given
X =4 .
11 23
[ ⇒ μY
X=
1
4
=
9
2
, and σ Y
X=
1
=
4
81 ]
13. (a) Show that: (i)
( ( y x ))= E ( xy )
E x E

(ii)
( y x))= E ( y )
E E(

(iii)
( y x))+ var [ E ( y x)]
var ( Y )= E var (

2
(b) A random variable X has mean μ1 and variance σ 1 .A random variable
2
Y has mean μ2 and variance σ 2 . The correlation coefficient of X and Y

is ρ 12 . Given that
E ( y x )=a+ bx , find the constants a and b in terms
2 2
of μ1 , μ2 , σ1 , σ2 and ρ 12 .

Page 5 of 6
 f (x)=¿ 1 for − 12 <x< 12 ¿ ¿¿¿
{
14. Let X have the marginal density
and let the conditional density of Y be

y
(){
f =¿ 1 , for x<y<x+1, −12 <x<0 ¿ −1, for −x<y<1−x, 0<x< 12 ¿ ¿¿¿
x
ρ 12 .
{
Find

Page 6 of 6