STAT 400 Stepanov

UIUC Practice Problems #7 Dalpiaz

SOLUTIONS
The following are a number of practice problems that may
be helpful for completing the homework, and will likely
be very useful for studying for exams.
1. Consider two continuous random variables X and Y with joint p.d.f.
 2 2
 81 x y 0 < x < K, 0 < y < K
f ( x, y ) = 
 0 otherwise



a) Find the value of K so that f ( x, y ) is a valid joint p.d.f.

KK
2 2 K5
1 = ∫∫ x y dx dy = . ⇒ K = 3.
00
81 243

b) Find P ( X > 3 Y ).

3x 3 

x y dy  dx
2 2
P(X > 3Y) = ∫ ∫
 81 
0 0 
3
1 1
= ∫ 729
x 4 dx =
15
.
0

OR

1 3 
 2 2  dy = … = 1 .
P(X > 3Y) = ∫  ∫ 81 x y dx  15
03 y 
c) Find P ( X + Y > 3 ).

3 3 
 2 2  dx
P(X + Y > 3) = ∫  ∫ 81 x y dy

0  3− x 
3
 9 − ( 3 − x ) 2  dx
1 2 
= ∫ 81
x

0

3
1
⋅  6 x 3 − x 4  dx
81 ∫ 
=

0

1  3 4 1 5  3 1  243 243 
= ⋅ x − x  = ⋅ −  = 0.90.
81  2 5  0
 81  2 5 


OR

3  3− x 3

P(X + Y > 3) = 1− ∫ ∫
2 2 
x y dy dx = 1 − ∫ x 2 ( 3 − x ) 2 dx
1
 81  81
0 0  0

3
1 1  3 1  3
= 1 − ⋅ ∫  9 x 2 − 6 x 3 + x 4  dx = 1 − ⋅  3 x 3 − x 4 + x 5 
 0
81   81  2 5 
0

1  243 243 
= 1− ⋅  81 − + = 0.90.
81  2 5 

d) Are X and Y independent? If not, find Cov ( X, Y ).

3
2 2 1
fX( x ) = ∫ 81
x y dy = x 2 ,
9
0 < x < 3,
0

3
2 2 2
fY( y ) = ∫ 81
x y dx = y ,
9
0 < y < 3.
0

f ( x , y ) = f X ( x ) ⋅ f Y ( y ). ⇒ X and Y are independent. Cov ( X, Y ) = 0.

2. Let X denote the number of times a photocopy machine will malfunction: 0, 1, 2, or 3
times, on any given month. Let Y denote the number of times a technician is called on
an emergency call. The joint p.m.f. p ( x, y ) is presented in the table below:

x
y 0 1 2 3 p Y( y )
0 0.15 0.30 0.05 0 0.50
1 0.05 0.15 0.05 0.05 0.30
2 0 0.05 0.10 0.05 0.20
p X( x ) 0.20 0.50 0.20 0.10 1.00

a) Find the probability P ( Y > X ).

P ( Y > X ) = p ( 0, 1 ) + p ( 1, 2 ) = 0.05 + 0.05 = 0.10.

b) Find p X ( x ), the marginal p.m.f. of X. ↑

c) Find p Y ( y ), the marginal p.m.f. of Y. ↑

d) Are X and Y independent? If not, find Cov ( X, Y ).

X and Y are NOT independent.

E ( X ) = 0 × 0.20 + 1 × 0.50 + 2 × 0.20 + 3 × 0.10 = 1.2.

E ( Y ) = 0 × 0.50 + 1 × 0.30 + 2 × 0.20 = 0.7.

E ( X Y ) = 1 × 0.15 + 2 × 0.05 + 3 × 0.05 + 2 × 0.05 + 4 × 0.10 + 6 × 0.05 = 1.2.

Cov ( X, Y ) = E ( X Y ) – E ( X ) × E ( Y ) = 1.2 – 1.2 × 0.70 = 0.36.

3. Let the joint probability density function for ( X , Y ) be

x+ y
f ( x, y ) = , x > 0, y > 0,
2
3 x + y < 3,
zero otherwise.

a) Find the probability P ( X < Y ).

intersection point:
y = x and x + 3 y = 3
3 3
x= and y =
4 4

3 4  3−3 x
 x + y 
P(X < Y) = ∫  ∫ 2 dy  dx
0  x 
3 4
9  27
= ∫  − 3 x  dx =
 4  32
.
0

OR

3 4  1−( y 3 )  3 4
 x+ y 
dx  dy = 1 − ∫  + y − y 2  dy =
1 1 8 27
P(X < Y) = 1− ∫  ∫ .
0 
2   4 3 9  32
y  0

b) Find the marginal probability density function of X, f X ( x ).

3−3 x
x+ y 9 3
fX( x ) = ∫ 2
dy =
4
− 3x + x 2,
4
0 < x < 1.
0
c) Find the marginal probability density function of Y, f Y ( y ).

1−( y 3 )
x+ y 1 1 5 2
f Y( y ) = ∫ 2
dx = + y−
4 3 36
y , 0 < y < 3.
0

d) Are X and Y independent? If not, find Cov ( X, Y ).

The support of ( X, Y ) is NOT a rectangle. ⇒ X and Y are NOT independent.

OR

f X, Y ( x, y ) ≠ f X ( x ) × f Y ( y ). ⇒ X and Y are NOT independent.

∞ 1
9 3 2
E( X ) = ∫ x ⋅ f X ( x ) dx = ∫ x ⋅  4 − 3 x + 4 x
 dx
−∞ 0


1
9 3 3 9 3 5
∫  4 x − 3 x
2
= + x  dx = − 1 + = .
0
4  8 16 16

∞ 3
y ⋅  + y −
5 2
y ⋅ f Y ( y ) dy =
1 1
E( Y ) = ∫ ∫ 4 3 36
y  dy

−∞ 0
3
1 1 5 3 9 405 21
∫  4 y + 3 y
2
= − y  dy = + 3 − = .
0
36  8 144 16

 3−3 x 1
x + y  1 x2 x 
E( X Y ) = ∫  xy⋅ dy dx = ∫  ( 3 − 3 x ) 2 + ( 3 − 3 x ) 3  dx
 ∫   
0  0
2
 0  4 6 
1
9
x + 9 x 3 − x 4  dx = − + −
45 2 9 9 15 9 9 6 3
= = ∫  2 x − 4 4  4 4 4 20
=
20
=
10
.
0

3 5 21 141
Cov ( X, Y ) = E ( X Y ) – E ( X ) × E ( Y ) = − × = − ≈ – 0.11016.
10 16 16 1280
4. Let the joint probability density function for ( X , Y ) be
x+ y
f ( x, y ) = , 0 < x < 2, 0 < y < 1, zero otherwise.
3

a) Find the probability P ( X > Y ).

y 1 
 x+ y 
P(X > Y) = 1− ∫  ∫ dx  dy

0 0
3 

1 
 y 2 y 2 
= 1− ∫ + dy
 6 3 
0  
1
y2 1 5
= 1− ∫ dy = 1 − = .
0
2 6 6

2 1 
 x+ y 
OR P(X > Y) = ∫  ∫ dx  dy = …

0 y
3 

1 x x+ y  2 1 x + y 
   
OR P(X > Y) = ∫  ∫ 3 dy  dx + ∫  ∫ 3 dy  dx = …
0 0  1 0 

b) Find the marginal probability density function of X, f X ( x ).

1
x+ y  xy y2  1 2 x +1
 
fX( x ) = ∫ 3
dy =
 3
+
6  0
=
6
, 0 < x < 2.
0  

c) Find the marginal probability density function of Y, f Y ( y ).

2
x+ y  x2 xy  2 2+2y
dx =  
fY( y ) = ∫ +

3  0
=
3
, 0 < y < 1.
0
3  6
d) Are X and Y independent? If not, find Cov ( X, Y ).

Since f ( x, y ) ≠ f X ( x ) ⋅ f Y ( y ), X and Y are NOT independent.

∞ 2  x 3 x 2  2 11
2x +1
E( X ) = ∫ x ⋅ f X ( x ) dx = ∫ x⋅ dx = 
 9
+  =
 0
.
−∞ 0
6  12  9

∞ 1  y2 y3  1 5
2+2y
E ( Y ) = ∫ y ⋅ f Y ( y ) dy = ∫ y ⋅ dy =  +  = .
3  3 9  0 9
−∞ 0  

2 1  2  x2 x   x3 x2  2 2
 x y ⋅ x + y dy  dx =  +  dx =   = .
E( X Y ) = ∫ ∫ 3  ∫  6 9   18
+
18  0 3
0 0  0    

2 11 5 1
Cov ( X, Y ) = E ( X Y ) – E ( X ) × E ( Y ) = − ⋅ = − ≈ – 0.012345679.
3 9 9 81
5. Two components of a laptop computer have the following joint probability density
function for their useful lifetimes X and Y (in years):

 (
−x 1 + y)
f ( x, y ) =  x e x ≥ 0, y ≥ 0
 0 otherwise

a) Find the marginal probability density function of X, f X ( x ).

∞ ∞
( −x 1 + y ) dy −x −x y
f X(x ) = ∫ xe = xe ∫e dy = e – x, x ≥ 0.
0 0

b) Find the marginal probability density function of Y, f Y ( y ).

∞
(
−x 1 + y ) dx 1
f Y(y ) = ∫ xe =
(1 + y ) 2
, y ≥ 0.
0

c) What is the probability that the lifetime of at least one component exceeds 1 year
(when the manufacturer’s warranty expires)?

1 1 
P( X > 1 ∪ Y > 1 ) = 1 – P( X ≤ 1 ∩ Y ≤ 1 ) = 1 − ∫  ∫ x e − x (1 + y ) dy  dx
 
0  0 
1 1  1
x e− x  dy dx = 1 − ∫ x e − x  − e − x  dx

−x y 1 1
= 1− ∫
∫
e 
0 0  0
 x x 

( e − x − e − 2 x )dx
1
 1  1
= 1− ∫ = 1 −  − e− x + e−2 x 
0
 2  0

   1
+ e − 1 − e − 2 ≈ 0.800212.
1 1 1
= 1 −  − e −1 + e − 2  +  − 1 +  =
 2   2 2 2

OR

P( X > 1 ∪ Y > 1 ) = P( X > 1 ) + P( Y > 1 ) – P( X > 1 ∩ Y > 1 ) = …

6. Let the joint probability density
function for ( X , Y ) be
1 –y
f ( x, y ) = e ,
2
0 < y < ∞, – y < x < y,
zero otherwise.

a) Find the marginal probability density function of X, f X ( x ).

∞
e x,
1 −y 1
If x < 0, fX( x ) = ∫ 2 e dy =
2
x < 0.
−x

∞
e – x,
1 −y 1
If x > 0, fX( x ) = ∫ 2 e dy =
2
x > 0.
x

fX( x ) =
1
e - | x |, – ∞ < x < ∞. ( double exponential )
2

b) Find the marginal probability density function of Y, f Y ( y ).

y
e dx = y e – y,
1 −y
fY( y ) = ∫ 2
0 < y < ∞. ( Gamma, α = 2, θ = 1 )
−y

c) Are X and Y independent? If not, find Cov ( X, Y ).

The support of ( X, Y ) is NOT a rectangle. ⇒ X and Y are NOT independent.

OR

f X, Y ( x, y ) ≠ f X ( x ) × f Y ( y ). ⇒ X and Y are NOT independent.

E ( X ) = 0, since the distribution of X is symmetric about 0.

E ( Y ) = 2, since Y has a Gamma distribution, α = 2, θ = 1.

∞ y  ∞  y 
 1 −y  1 −y  
E( X Y ) = ∫  ∫ e dx  dy = ∫ e  ∫ dx  dy = 0.
0  − y   
2 2
 0 −y 

Cov ( X, Y ) = E ( X Y ) – E ( X ) × E ( Y ) = 0.

Recall: Independent ⇒ Cov = 0

Cov = 0 ⇒
X Independent
7. Suppose Jane has a fair 4-sided die, and Dick has a fair 6-sided die. Each day,
they roll their dice at the same time (independently) until someone rolls a “1”.
(Then the person who did not roll a “1” does the dishes.) Find the probability
that …

x −1
p J ( x ) =   ⋅   , x = 1, 2, 3, … ,
3 1
4 4
y −1
p D ( y ) =   ⋅   , y = 1, 2, 3, … .
5 1
6 6

a) they roll the first “1” at the same time (after equal number of attempts);

∞ ∞ k −1 k −1
p J ( k )⋅ p D ( k ) 3
⋅   ⋅   ⋅  
1 5 1
∑ = ∑  
4 6 6
k =1 k =1  4 

 1  ∞  15 
n
 1  1 1
=  ⋅ ∑   =  ⋅ = .
 24  n = 0  24   24  1 − 15 9
24

OR

(J D) or ( J' D' ) ( J D ) or ( J' D' ) ( J' D' ) ( J D ) or …

1 1
 ⋅ 
1 1 3 5 1 1 3 5 3 5 1 1 4 6 = 1 .
 ⋅  +  ⋅  ⋅  ⋅  +  ⋅  ⋅  ⋅  ⋅  ⋅  + ... =
4 6 4 6 4 6 4 6 4 6 4 6  3 5 9
1−  ⋅ 
4 6
b) Dick rolls the first “1” before Jane does.

∞ ∞ ∞  5  k −1  1  ∞  3  m −1  1 
∑ ∑ p J ( m )⋅ p D ( k ) = ∑   ⋅ ⋅ ∑   ⋅ 
k =1 m = k +1 k =1  6   6  m = k +1  4  4

∞  5  k −1  1   3  k  1  ∞  15 
n
1 1 1
= ∑ 6 ⋅ ⋅
    = ⋅
  ∑   =  ⋅ = .
k =1    6   4   8  n=0  24   8  1−
15 3
24

OR

( J' D ) or ( J' D' ) ( J' D ) or ( J' D' ) ( J' D' ) ( J' D ) or …

3 1
 ⋅ 
3 1 3 5 3 1 3 5 3 5 3 1 4 6 = 1 .
 ⋅  +  ⋅  ⋅  ⋅  +  ⋅  ⋅  ⋅  ⋅  ⋅  + ... =
4 6 4 6 4 6 4 6 4 6 4 6 3 5 3
1−  ⋅ 
4 6
8. Dick and Jane have agreed to meet for lunch between noon (0:00 p.m.) and
1:00 p.m. Denote Jane’s arrival time by X, Dick’s by Y, and suppose X and Y
are independent with probability density functions

 2  2 y 0 ≤ y ≤1
f X ( x ) =  3 x 0 ≤ x ≤1
f Y (y) = 
 0 otherwise  0 otherwise

a) Find the probability that Jane arrives before Dick. That is, find P ( X < Y ).

f ( x, y ) = 6 x 2 y, 0 ≤ x ≤ 1, 0 ≤ y ≤ 1.

1 y  1 y 
   
∫ ∫ ∫ ∫
2 2
P ( X < Y ) =  6 x y dx  dy = y  6 x dx  dy
0  0 
 0  0 


∫y( )
1 1
dy =  y 5  = .
y 2 1 2
2 x 3 dy ∫2 y
4
= =
0 5 0 5
0 0

OR

11  1 
( )
1 1
   
∫∫ ∫ ∫ ∫
2 1
P ( X < Y ) =  6 x y dy  dx = x 2
2 2
 6 y dy  dx = x 3 y x dx

0x
  
 0 x  0

∫ (3 x )
1
2  3 1 2
= − 3 x 4 dx =  x 3 − x 5  = .
 5 0 5
0
b) Find the expected amount of time Jane would have to wait for Dick to arrive.

Hint 1: If Dick arrives first ( that is, if X > Y ), then Jane’s waiting time is zero.
If Jane arrives first ( that is, if X < Y ), then her waiting time is Y – X.
∞ ∞
Hint 2: E ( g( X, Y ) ) = ∫ ∫ g ( x, y) ⋅ f ( x, y) dx dy
−∞ −∞

f ( x, y ) = 6 x 2 y, 0 ≤ x ≤ 1, 0 ≤ y ≤ 1.

 y>x Jane is waiting for Dick.

Jane’s waiting time = y – x

 x>y Dick is waiting for Jane.

Jane’s waiting time = 0

1 y  1x 
   
∫  ∫ ( y − x ) ⋅ 6 x y dx  dy + ∫  ∫ 0 ⋅ 6 x y dy  dx
2 2

0 0  00 

1 y  1 y 
   
= ∫  ∫ 6 x y dx  dy − ∫  ∫ 6 x 3 y dx  dy
2 2

0  0 
 0  0 


1 1
1 1 1
∫2y dy − ∫ 1.5 y 5 dy =
5
= − = hour = 5 minutes.
0 0
3 4 12
9. Suppose that ( X, Y ) is uniformly distributed over the region defined by
– 1 ≤ x ≤ 1 and 0 ≤ y ≤ 1 – x 2. That is,

f ( x, y ) = C, – 1 ≤ x ≤ 1, 0 ≤ y ≤ 1 – x 2, zero elsewhere.

a) What is the joint probability density function of X and Y ? That is, find C.

1  1− x 2 
( )
1
 
∫  ∫  ∫ 1 − x dx
2
dy dx =
−1  0  −1

 x3  1 4
=  x−  = .
 3  −1 3
 

3
⇒ f X , Y ( x, y ) = , – 1 ≤ x ≤ 1, 0 ≤ y ≤ 1 – x 2.
4

b) Find the marginal probability density function of X, f X ( x ).

( )
1− x 2
3 3
f X( x ) = ∫ 4
dy =
4
1− x 2 , – 1 ≤ x ≤ 1.
0

c) Find the marginal probability density function of Y, f Y ( y ).

y = 1 – x2 x = ± 1− y

1− y
3 3
f Y( y ) = ∫ 4
dx =
2
1− y , 0 ≤ y ≤ 1.
− 1− y
10. Let T 1 , T 2 , … , T k be independent Exponential random variables.
1
Suppose E ( T i ) = , i = 1, 2, … , k.
λi
–λ t
That is, f T ( t ) = λ i e i , t > 0, i = 1, 2, … , k.
i

Denote T min = min ( T 1 , T 2 , … , T k ).

a) Show that T min also has an Exponential distribution. What is the mean of T min ?

Hint: Consider P ( T min > t ) = P ( T 1 > t AND T 2 > t AND … AND T k > t ).

Since T 1 , T 2 , … , T k are independent,

P ( T min > t ) = P ( T 1 > t AND T 2 > t AND … AND T k > t )

= P( T1 > t ) × P( T2 > t ) × … × P( Tk > t )

= e – λ1 t × e – λ2 t × … × e – λk t

= e – ( λ 1 + λ 2 + … + λ k ) t, t > 0.

FT ( t ) = P ( T min ≤ t ) = 1 – P ( T min > t ) = 1 – e – ( λ 1 + λ 2 + … + λ k ) t, t > 0.

min

fT ( t ) = ( λ 1 + λ 2 + … + λ k ) e – ( λ 1 + λ 2 + … + λ k ) t, t > 0.
min

1
⇒ T min has an Exponential distribution with mean .
λ 1 + λ 2 + ... + λ k
b) Find P ( T 1 = T min ) = P ( T 1 is the smallest of T 1 , T 2 , … , T k )

= P ( T 1 < T 2 AND … AND T 1 < T k ).

1 λ
“Hint”: A good place to start is to consider T 1 , T 2 and show that P ( T 1 < T 2 ) = .
λ1 + λ 2

∞ ∞ 

P ( T 1 < T 2 ) = ∫  ∫ λ 1 e −λ 1 t1 λ 2 e −λ 2 t 2 dt 2  dt 1

0  t1


∞
−λ 1 t1 λ1
= ∫ λ1 e e −λ 2 t1 dt 1 = .
0
λ1 + λ 2

Since T 1 , T 2 , … , T k are independent, their joint probability density function is

f ( t 1 , t 2 , … , t k ) = λ 1 e −λ 1 t1 λ 2 e −λ 2 t 2 . . . λ k e −λ k t k ,
t 1 > 0 , t 2 > 0, … , t k > 0.

P ( T 1 = T min ) = P ( T 1 < T 2 AND … AND T 1 < T k )

∞ ∞ ∞ 

= ∫  ∫ ... ∫ λ 1 e −λ 1 t1 λ 2 e −λ 2 t 2
... λ k e −λ k t k
dt 2 ... dt k  dt 1

0  t1 t1


∞ ∞  ∞ 
= ∫ λ 1 e −λ 1 t1  ∫ λ 2 e −λ 2 t 2 dt 2  ...  ∫ λ k e −λ k t k dt k  dt 1
t  t 
0  1   1 
∞
= ∫ λ1 e
−λ 1 t1
e −λ 2 t1 ... e −λ k t1 dt 1
0

λ1
= .
λ 1 + λ 2 + ... + λ k