5-5
The joint probability distribution of X 1 and X 2 is
because X 1 and X 2 are independent. Let Y 1 h 1 (X 1 , X 2 ) and Y 2 h 2 (X 1 , X 2 )
X 1 X 2. The inverse solutions of y 1 and y 2 x 1 x 2 are and
, and it follows that
Therefore
and from Equation S5-4 the joint probability distribution of Y 1 and Y 2 is
for y 1
0, y 2
0. We need to find the distribution of. This is the marginal prob-
ability distribution of Y 1 , or
An important application of Equation S5-4 is to obtain the distribution of the sum of two
independentrandom variables X 1 and X 2. Let Y 1 X 1 X 2 and let Y 2 X 2. The inverse so-
lutions are x 1 y 1 y 2 and x 2 y 2. Therefore,
x 2
y 1
0
x 2
y 2
1
x 1
y 1
1
x 1
y 2
1
1
11 y 122
, y 1
0
0
4 e^2 y^2 3 y 2
11 y 1224 dy 2
fY 11 y 12
0
fY 1 Y 21 y 1 , y 22 dy 2
Y 1 X 1
X 2
4 e^2 y^2 y 2
11 y 122
4 e^23 y^1 y^2
11 y^12 y^2
11 y^124 `
y 2
11 y 122
`
fY 1 Y 2 1 y 1 , y 22 fX 1 X 2 3 u 11 y 1 , y 22 , u 21 y 1 , y 2240 J 0
J∞
y 2
11 y 122
y 1
11 y 12
y 2
11 y 122
1
11 y 12
∞
y 2
11 y 122
x 2
y 1
y 2 c
1
11 y 122
d,
x 2
y 2
c
1
11 y 12
d
x 1
y 1
y 2 c
1
11 y 122
d,
x 1
y 2
c
y 1
11 y 12
d
x 2 y 2
11 y 12
x 1
x 2 x 1 y 1 y 2
11 y 12
X 1
X 2
fX 1 X 2 1 x 1 , x 22 4 e^21 x^1 x^22 , x 1 0, x 2 0
PQ220 6234F.CD(05) 5/13/02 4:51 PM Page 5 RK UL 6 RK UL 6:Desktop Folder:TEMP WORK:MONTGOMERY:REVISES UPLO D CH114 FIN L:Quark F