Suggested Solutions to Tutorial Exercises

Rice, J.A. Mathematical Statistics and Data Analysis. 3th edition.

Chapter 3:

8) Let X and Y have the joint density

6
fXY (x, y) = (x + y)2 , 0 ≤ x ≤ 1, 0 ≤ y ≤ 1.
7

a. By integrating over the appropriate regions, find (i) P (X > Y ), (ii) P (X + Y ≤ 1), (iii)
P (X ≤ 1/2).

(i) We can let the limits of integration be 0 to 1 for x, and 0 to x for y, so

Z ∞ Z x
P (X > Y ) = fXY dydx
−∞ −∞
Z 1Z x
6
= (x + y)2 dydx
0 0 7
Z 1
6 1 x
= (x + y)3 dx
7 0 3 0
Z 1
=2 x3 dx
0
1
=
2

(ii) Here we can again let the limits of integration be 0 to 1 for x, but the range for y is now
0 to 1 − x. Thus
Z 1 Z 1−x
6
P (X + Y ≤ 1) = (x + y)2 dydx
0 0 7
6 11
Z
1−x
= (x + y)3 dx
7 0 3 0
2 1
Z
= 1 − x3 dx
7 0
3
=
14

University of Johannesburg STA2B10/STA02B2 Tutorial Exercise Solutions, p.1

 (iii) In this case the limits are easy; from 0 to 1/2 for x and 0 to 1 for y
Z 1/2 Z 1
6
P (X ≤ 1/2) = (x + y)2 dydx
0 0 7
2 1/2
Z
= (x + 1)3 − x3 dx
7 0
1 1/2
= [(x + 1)4 − x4 ]
14 0
4
=
14

b. Find the marginal densities of X and Y

Z ∞
fX = fXY dy
−∞
Z 1
6
fX (x) = (x + y)2 dy
0 7
2 1
= (x + y)3
7 0
2
= [(x + 1)3 − x3 ]
7
2
= [3x2 + 3x + 1], 0 ≤ x ≤ 1.
7

as the joint density is symmetric in x and y, an identical exercise yields

2
fY (y) = [3y 2 + 3y + 1], 0 ≤ y ≤ 1.
7

c. Find the two conditional densities.

fXY
fX|Y =
fY
6 2
7 (x + y)
fX|Y (x|y) = 2 2
7 (3y + 3y + 1)
(x + y)2
=3 , 0 ≤ x ≤ 1.
(3y 2 + 3y + 1)

Arguing by symmetry again gives

(x + y)2
fY |X (y|x) = 3 , 0 ≤ y ≤ 1.
(3x2 + 3x + 1)

12) Let
fXY (x, y) = c(x2 − y 2 )e−x , 0 ≤ x < ∞, −x ≤ y ≤ x

a. Find c.

To do this, we need to investigate the joint density over its entire allowable region, set the

University of Johannesburg STA2B10/STA02B2 Tutorial Exercise Solutions, p.2

 result equal to 1, and solve for c.
Z ∞ Z ∞
1= fXY dydx
Z−∞ −∞
∞Z x
= c(x2 − y 2 )e−x dydx
0 −x
Z ∞ x
y3

= 2
cx y − c e−x dx
0 3 −x
Z ∞ 3

x
= 2cx3 − 2c e−x dx
0 3
Z ∞
4
= c x3 e−x dx.
3 0
Now at this point, we can proceed in two equivalent ways. We can do the integration by parts,
getting Z ∞
∞ ∞ ∞
−x3 e−x 0
− 3x2 e−x 0
− 6xe−x 0
+ 6e−x dx = 6
0
or we can recognise that the above integral is the Gamma function with parameters 3+1 =
4 and Γ(4) = (4 − 1)! = 6. This integral occurs sufficiently often that it is worth learning to
look for it. At any rate,
4 1
1 = c × 6 = 8c −→ c =
3 8

b. Find the marginal densities.

Well, we went a long way towards finding the marginal density for x in solving part a.;
Z x
fX (x) = c(x2 − y 2 )e−x dydx
−x
4
= cx3 e−x
3
1
= x3 e−x , 0 ≤ x < ∞
6
which we recognise as a Gamma(α = 4, λ = 1) density. In solving for fY , we need to be a bit
more careful with the limits of integration; for a specific value of y, x ranges from |y| to ∞. It
is also easier to split up the x2 and y 2 parts of the joint density in doing the integration.
Z ∞ Z ∞
2 −x
fY (y) = cx e dx − cy 2 e−x dx
|y| |y|
Z ∞ Z ∞
∞ ∞
2 −x −x −x
= −cx e − 2cxe + 2ce dx − cy 2 e−x dx
|y| |y| |y| |y|
∞ ∞
= c|y|2 e−|y| + 2c|y|e−|y| − 2ce−x + cy 2 e−x
|y| |y|
h i
= c (y 2 + 2|y| + 2) − y 2 e−|y|
1
= (|y| + 1)e−|y| , −∞ < y < ∞.
4

c. Find the conditional densities.

fXY (x, y)
fY |X (y|x) =
fX (x)
c(x2 − y 2 )e−x
= 4 3 −x
3 cx e
3 x2 − y 2
= × , −x ≤ y ≤ x
4 x3

University of Johannesburg STA2B10/STA02B2 Tutorial Exercise Solutions, p.3

 and

fXY (x, y)
fX|Y (x|y) =
fY (y)
c(x2 − y 2 )e−x
=
2c(|y| + 1)e−|y|
1 (x2 − y 2 )e−(x−|y|)
= × , |y| ≤ y < ∞.
2 |y| + 1

15) Suppose that X and Y have the joint density function

p
f (x, y) = c 1x2 − y 2 , x2 + y 2 ≤ 1

a. Find c.
Z 1 Z √1−y2 p
√ c 1 − x2 − y 2 dxdy = 1
−1 − 1−y 2
Z 2π Z 1 p
c 1 − r2 rdrdθ = 1
0 0
Z 2π
c 1
− (1 − r2 )3/2 dθ = 1
3 0 0
Z 2π
c
dθ = 1
3 0
c
(2π) = 1
3
3
∴c=
2π

c. Find P (X 2 + Y 2 ≤ 12 )

Z 1/2 Z √1/2−y2
3 p
√ 1 − x2 − y 2 dxdy
−1/2 − 1/2−y 2 2π
√
Z 2π Z 2/2 p
3
= 1 − r2 rdrdθ
2π 0 0
√
Z 2π
1 2 3/2
2/2
=− (1 − r ) dθ
2π 0 0
Z 2π " √ #
1 1−2 2
=− √ dθ
2π 0 2 2
" √ #
1 1−2 2 2π
=− √ θ
2π 2 2 0
√
2 2−1
= √
2 2
= 0.6464

16) If X1 is uniform on [0, 1], and, conditional on X1 , X2 , is uniform on [0, X1 ], find the joint and
marginal distributions of X1 and X2 .
From the statement of the problem, the densities that we are given are fX1 and fX2 |X1 . These can

University of Johannesburg STA2B10/STA02B2 Tutorial Exercise Solutions, p.4

 easily be used to construct the joint density function, as

fX1 X2 (x1 x2 ) = fX1 (x1 )fX2 |X1 (x2 |x1 )

1 1
=1× = , 0 < x1 < 1, 0 < x2 < x1 .
x1 x1

Now, starting with the joint we can integrate to get the marginals:

fX1 (x1 ) = 1, 0 < x1 < 1 (given)

Z 1
1
fX2 (x2 ) = dx1
x2 x 1
1
= log(x1 )
x2
= − log(x2 ), 0 < x2 < 1.

18) Let X and Y have the joint density function

fXY (x, y) = k(x − y), 0≤y≤x≤1

and 0 elsewhere.

a. Sketch the region over which the density is positive and use it in determining limits of integration
to answer the following questions.

The region is a triangular with vertices at (0,0), (1,0), and (1,1).

b. Find k.

We need to integrate the density over its entire positive region, set the values to 1, and solve
for k.
Z 1Z x
1= k(x − y)dydx
0 0
1  x
y2
Z 
= k xy − dx
0 2
0
1
x2
Z
= k dx
0 2
1
x3 k
=k =
6 6
0

so k = 6.
c. Find the marginal densities of X and Y .

Using part b.,

Z x
fX (x) = k(x − y)dy
0
x2
=k = 3x2 , 0<x<1
2

University of Johannesburg STA2B10/STA02B2 Tutorial Exercise Solutions, p.5

 and
Z 1
fY (y) = k(x − y)dx
y
 1
x2

=k − xy
2
y
   2 
1 y 2
=k −y −k −y
2 2
 2 
y 1
=k −y+
2 2
= 3 (1 − y)2 , 0 < y < 1.

d. Find the conditional densities of Y given X and X given Y .

fXY (x, y) 6(x − y) x−y

fY |X (y|x) = = =2 2 , 0<y<x
fX (x) 3x2 x
fXY (x, y) 6(x − y) x−y
fX|Y (x|y) = = 2
=2 , y<x<1
fY (y) 3(1 − y) (1 − y)2

19) Suppose that two components have independent exponentially distributed lifetimes, T1 and T2 , with
parameters α and β, respectively. Find

(a) P (T1 > T2 )

The limits of integration here are 0 to t1 for t2 , and 0 to ∞ for t1

Z ∞ Z t1
P (T1 > T2 ) = fT1 T2 (t1 , t2 )dt2 dt1
0 0
Z ∞Z t1
= fT1 (t1 )fT2 (t2 )dt2 dt1 (independence)
0 0
Z ∞ Z t1 
= fT1 (t1 ) fT2 (t2 )dt2 dt1
Z0 ∞ h
0
i
= fT1 (t1 ) 1 − e−βt1 dt1 (cdf of an exponential function)
0
Z ∞ Z ∞
= fT1 (t1 )dt1 − αe−(α+β)t1 dt1
0 0
α −(α+β)t1 ∞
 
=1− − e
α+β 0
α β
=1− = .
α+β α+β

Note that this does something sensible - if we let α = β, so that the two random variables are
identically distributed, then the chances are equal that one is greater than the other.

(b) P (T1 > 2T2 ).

University of Johannesburg STA2B10/STA02B2 Tutorial Exercise Solutions, p.6

 This is much like part (a) but the limits of integration for t2 are now from 0 to t1 /2.
Z ∞ Z t1 /2
P (T1 > 2T2 ) = fT1 T2 (t1 , t2 )dt2 dt1
Z0 ∞ 0
h i
= fT1 (t1 ) 1 − e−βt1 /2 dt1 (cdf of an exponential function)
0
Z ∞
=1− αe−(α+β/2)t1 dt1
0
α β/2
=1− = .
α + β/2 α + β/2

Note that this is equivalent to what we got in part (a) if we change the value of the parameter
of T2 from β to β/2. This fits with the result we found earlier (Chapter 2 problem 61) where we
found that if X has a Gamma(α, λ) distribution, then cX has a Gamma(α, λ/c) distribution.
The exponential distribution is a Gamma distribution with α = 1, so letting c = 2 the results
follows.

University of Johannesburg STA2B10/STA02B2 Tutorial Exercise Solutions, p.7