5-2
We will also state this result as follows.
A very important application of Equation S5-2 is in finding the distribution of a random vari-
able Y 1 that is a function of two other random variables X 1 and X 2. That is, let Y 1 h 1 (X 1 , X 2 )
where X 1 and X 2 are discrete random variables with joint distribution We want to
find the probability distribution of Y 1 , say, To do this, we define a second function Y 2
h 2 (X 1 ,X 2 ) so that the one-to-one correspondence between the points (x 1 , x 2 ) and (y 1 , y 2 ) is main-
tained, and we use the result in Equation S5-2 to find the joint probability distribution of Y 1 and
Y 2. Then the distribution of Y 1 alone is found by summing over the y 2 values in this joint distribu-
tion. That is, is just the marginal probability distributionof Y 1 , or
EXAMPLE S5-2 Consider the case where X 1 and X 2 are independent Poisson random variables with parameters
1 and 2 , respectively. We will find the distribution of the random variable Y 1 X 1 X 2.
The joint distribution of X 1 and X 2 is
because X 1 and X 2 are independent. Now to use Equation S5-2 we need to define a second func-
tionY 2 h 2 (X 1 , X 2 ). Let this function be Y 2 X 2. Now the solutions for x 1 and x 2 are x 1 y 1 y 2
and x 2 y 2. Thus, from Equation S5-2 the joint probability distribution of Y 1 and Y 2 is
Because x 1 0, the transformation x 1 y 1 y 2 requires that x 2 y 2 must always be less than
or equal to y 1. Thus, the values of y 2 are 0, 1,... , y 1 , and the marginal probability distribution
of Y 1 is obtained as follows:
fY 11 y 12 a
y 1
y 2 0
fY 1 Y 21 y 1 , y 22 a
y 1
y 2 0
e^1 ^1 ^22 11 y^1 y^22 2 y^2
1 y 1 y 22! y 2!
fY 1 Y 21 y 1 , y 22
e^1 ^1 ^22 11 y^1 y^22 2 y^2
1 y 1 y 22! y 2!
, y 1 0, 1, 2, p , y 2 0, 1, p , y 1
e^1 ^1 ^22 x 11 x 22
x 1! x 2!
, x 1 0, 1, p , x 2 0, 1, p
e^1 x 11
x 1!
e^2 x 22
x 2!
fX 1 X 21 x 1 , x 22 fX 11 x 12 fX 21 x 22
fY 11 y 12 a
y 2
fY 1 Y 21 y 1 , y 22
fY 11 y 12
fY 11 y 12.
fX 1 X 21 x 1 , x 22.
Suppose that X 1 and X 2 are discreterandom variables with joint probability distribu-
tion and let Y 1 h 1 (X 1 , X 2 ) and Y 2 h 2 (X 1 , X 2 ) define one-to-one trans-
formations between the points (x 1 , x 2 ) and (y 1 , y 2 ) so that the equations y 1 h 1 (x 1 , x 2 )
and y 2 h 2 (x 1 , x 2 ) can be solved uniquely for x 1 and x 2 in terms of y 1 and y 2. Let this
solution be x 1 u 1 (y 1 , y 2 ) and x 2 u 2 (y 1 , y 2 ). Then the joint probability distribution
of Y 1 and Y 2 is
fY 1 Y 21 y 1 , y 22 fX 1 X 23 u 11 y 1 , y 22 , u 21 y 1 , y 224 (S5-2)
fX 1 X 21 x 1 , x 22 ,
PQ220 6234F.CD(05) 5/13/02 4:51 PM Page 2 RK UL 6 RK UL 6:Desktop Folder:TEMP WORK:MONTGOMERY:REVISES UPLO D CH114 FIN L:Quark F