Académique Documents
Professionnel Documents
Culture Documents
..
Bivariate Probability Distributions and Sampling
Distributions
6.2
a.
p ( x, y ) =
b.
1
36
1 x 6, 1 y 6
1
1
1
1
1
1
6 1
+ + + + +
=
=
36 36 36 36 36 36 36 6
= p1 (6) =
= p2 (6) =
1
6
1
6
p1 ( x, y )
p2 ( y )
p ( x, 1)
p2 (1)
1
p(1, 1) 36 1
p1 (1|1) =
=
=
1 6
p2 (1)
6
1
p (2, 1) 36 1
p1 (2 |1) =
=
=
1 6
p2 (1)
6
104
Chapter 6
1
p (6, 1) 36 1
p1 (6 |1) =
=
=
1 6
p2 (1)
6
6.4
In fact, p1 ( x | y ) =
1
for 1 x 6, 1 y 6
6
and p2 ( y | x) =
1
for 1 x 6, 1 y 6
6
d.
a.
b.
c.
0
0.0625
0.1825
1
0.1825
0.5625
p1 ( x | y ) =
p1 ( x, y )
p2 ( y )
p1 ( 0 | 0 ) =
p1 (0,0) 0.0625
=
= 0.2551
p2 (0) 0.2450
p1 (1| 0 ) =
p1 (1,0) 0.1825
=
= 0.7449
p2 (0) 0.2450
p1 ( 0 |1) =
p1 (0,1) 0.1825
=
= 0.2450
p2 (1) 0.7450
p1 (1|1) =
p1 (1,1) 0.5625
=
= 0.7550
p2 (1) 0.7450
p1 ( x) =
p ( x, y )
y
105
6.6
a.
3 2 2
0 0 3
p (0, 0) = = 0
7
3
3 2 2
1 0 2
3 1 1 3
p (1, 0) = =
=
35
35
7
3
3 2 2
2 0 1
3 1 2 6
=
p (2, 0) = =
35
35
7
3
3 2 2
3 0 0
1 1 1 1
=
p (3, 0) = =
7
35
35
3
3 2 2
0 1 2
1 2 1 2
=
p (0, 1) = =
35
35
7
3
3 2 2
1 1 1
3 2 2 12
=
p (1, 1) = =
35
35
7
3
3 2 2
2 1 0
3 2 1 6
=
p (2, 1) = =
7
35
35
3
p(3, 1) = 0
106
Chapter 6
3 2 2
0 2 1
1 1 2 2
=
p (0, 2) = =
7
35
35
3
3 2 2
1 2 0
3 1 1 3
p (1, 2) = =
=
35
35
7
3
p(2, 2) = p(3, 2) = 0
x
0
0
y 1
2
b.
p1 ( x) =
0
2
35
2
35
p ( x,
1
3
35
12
35
3
35
2
6
35
6
35
3
1
35
y)
3 12 3 18
+ +
=
35 35 35 35
6
6
12
+ +0=
35 35
35
1
+0+0
35
x
p(x)
6.8
2
2
4
+
=
35 35 35
0
4
35
1
18
35
2
12
35
3
1
35
There are four possible combinations of x and y: (0, 0), (0, 1), (1, 0), (1, 1). Substituting
these values into the formula for p( x, y ), we obtain the following probabilities:
p (0, 0) = p 0+0 q 2(0+0) = q 2
107
p( x,
x
y) = 1
6.10
a.
f ( y) =
2y
f ( x, y )dx =
2y
e y 10
e y 10
e y 10 e y 10 e y 10
dx =
x =
=
10 y
10 y y
5
10
10
6.12
a.
f ( x, y )dx dy = 1
ce
x2
dx dy = ce
0 0
x2
y dx
0
cxe
x2
2
ce x
dx =
2
0
c c
=0 = c=2
2 2
b.
f1 ( x) =
f1 ( x) dx = 2 xe
f ( x, y )dy = 2e x dy = 2e x y = 2 xe x
0
x2
dx = e
x2
= 0 (1) = 1
c.
108
f 2 ( y | x) =
f ( x , y ) 2e x
1
=
=
x2
f1 ( x)
x
2 xe
0 y x
Chapter 6
+ +
6.14
a.
Note
f ( x, y )dx dy = 1
x2
cxy dx dy = cxy dx dy = cy dy
Therefore,
2
0 0
0
+ +
1 1
1
12 02
cy
cy 2
c
dy =
= cy dy =
= =1
2
2(2)
4
2 2
0
0
0
1
Since
c
=1 c = 4
4
+
b.
f1 ( x) =
f2 ( y) =
c.
f1 ( x | y ) =
4 xy 2
4x
= 2x
f ( x, y )dy = 4 xy dy =
=
2
2
0
1
4 yx 2
4y
= 2y
f ( x, y ) dx = 4 xy dx =
=
2
2
f ( x, y )
f2 ( y)
6.18
a.
E ( x) =
f1 ( x | y ) =
f ( x, y ) 4 xy
=
= 2x
f2 ( y)
2y
f 2 ( y | x) =
f ( x, y ) 4 xy
=
= 2y
f1 ( x)
2x
x =0
b.
E ( x + y ) = E ( x) + E ( y )
Need to find E ( y ) .
E ( y) =
y =0
a.
109
x y if 1 x 2; 0 y 1
Therefore, f ( x, y ) =
elsewhere
0
+
E ( x) =
xf ( x)dx
1
f1 ( x) =
y2
1
f ( x, y )dy = ( x y )dy = xy = x
2
2
0
1
E ( x) = x x dx =
2
1
1
b.
x3
1 2
2 1
x
x
dx
=
2
3 2(2)
23 22 13 12 8 4 1 1 7 3 28 9
= + = =
3 2(2) 3 2(2) 3 4 3 4 3 4 12 12
19
12
3
y
2
0 y 1
1
1
3 2 y3
3
y
Therefore, E ( y ) = y y dy = y y 2 dy =
2
2
2(2)
3
0
0
0
1
c.
3(12 ) 13 9 4
5
= =
4
3 12 12 12
E ( x + y ) = E ( x) + E ( y ) =
19 5 24
+ =
=2
12 12 12
+ +
d.
E ( xy ) =
xy
2 1
f ( x, y )dy dx =
1 0
2 1
( x
1 0
110
xy( x y)dy dx
y xy )dy dx =
x 2 y 2 xy 3
dx
2
3
0
Chapter 6
6.24
(1)
(2)
x2 x
x3
x2
dx =
2 3
2(3) 3(2)
23 22 13 12 4 2
= =
6 6 6 6 6 3
+ +
+ +
E (c ) =
cf ( x, y)dy dx = c
E ( cg ( x, y ) ) =
f ( x, y )dy dx = c 1 = c
+ +
c g ( x, y) f ( x, y)dy dx
+ +
=c
g ( x, y) f ( x, y)dy dx = cE [ g ( x, y)]
(3)
E [ g1 ( x, y ) + g 2 ( x, y ) +
+ g k ( x, y ) ]
+ +
[ g ( x, y ) + g ( x, y ) +
1
+ g k ( x, y )] f ( x, y ) dy dx
+ +
[ g ( x, y ) f ( x , y ) + g ( x, y ) f ( x, y ) +
1
+ g k ( x, y ) f ( x, y ) ]dy dx
+ +
+ +
g1 ( x, y ) f ( x, y )dy dx +
g ( x, y) f ( x, y)dy dx
2
+ +
g ( x, y) f ( x, y)dy dx
k
= E [ g1 ( x, y )] + E [ g 2 ( x, y ) ] +
6.26
+ E [ g k ( x, y ) ]
1
36
1
1
p1 ( x) = , p2 ( y ) =
6
6
for x, y = 1, 2, , 6
111
To show independence,
p ( x, y ) = p1 ( x) p2 ( y )
1 1 1
=
36 6 6
p( x, y ) p1 ( x) p2 ( y )
1
f ( x, y ) = xe x / 2e y / 2
8
1
where g ( x) = xe x / 2
8
h( y ) = e y / 2
x and y are independent
6.32
f ( x, y ) = x y
f1 ( x) = x
f2 ( y) =
1
2
3
y
2
1 3
f1 ( x) f 2 ( y ) = x y f ( x, y )
2 2
6.34
E ( xy ) =
xy f ( x,
y )dx dy
xy f ( x) f ( y)dx dy
1
by independence
112
Chapter 6
x f ( x) y f ( y)dx dy
1
x f1 ( x)dx
6.36
y f ( y)dy = E ( x) E ( y)
2
Cov( x, y ) = E ( xy ) 12
E ( xy ) =
xy p( x, y)
x =1 y =1
1
1
1
= 1(1) + 1(2) + 1(3) +
36
36
36
6
1 21
+ 6 =
6 6
1 = E ( x) = x p1 ( x) = 1 + 2 +
6
6
x =1
1 441
+ 6(6) =
36 36
2 = E ( y ) = y p2 ( y ) = 1 + 2 +
6
6
y =1
Cov( x, y ) =
6.38
a.
1 21
+ 6 =
6 6
441 21 21
=0
36 6 6
xyp( x, y) 1.69(1.77)
x = 0 y =0
b.
12 = E ( x 2 ) 12 = x 2 p1 ( x) 1.692
x =0
2
1 = .8339 = .9132
3
22 = E ( y 2 ) 22 = y 2 p2 ( y ) 1.77 2
y =0
113
2 = .8771 = .9365
=
6.40
a.
Cov( x, y )
1 2
.0313
= .0366
(.9132)(.9365)
19
5
2
, E ( y ) = , and E ( xy ) =
12
12
3
Therefore,
Cov( x, y ) = E ( xy ) E ( x) E ( y )
=
b.
Cov( x, y ) =
2 19 5 2 95
96 95
1
=
=
=
3 12 12 3 144 144 144 144
1
= .0069444
144
1 = 12 , 12 = E ( x 2 ) [ E ( x) ]
1
x2
E ( x 2 ) = x 2 f1 ( x)dx = x 2 x dx = x3 dx
2
2
1
1
1
1
x 3 16 8 1 1 32 1 31
= x4 = =
=
4
6 1 4 6 4 6 12 12 12
2
12 =
31 19
11
=
12 12 144
1 =
11
144
2 = 22 , 22 = E ( y 2 ) [ E ( y ) ]
E ( y ) = y 2 y dy
2
0
2
114
Chapter 6
3y2
y3 y 4 1 1
1
y 3 dy =
= 0=
=
2
2
4
2
4
4
0
0
1 5
11
11
2 =
= =
4 12 144
144
2
2
6.42
Cov( x, y )
1 2
1
1
1
144
=
= 144 =
11
11
11
11
144
144 144
Cov( x, y ) = E ( xy ) E ( x) E ( y )
=
a1
a2
xy p ( x, y )
x = 0 y =0
a1
xp1 ( x)
x =0
a2
yp ( y)
2
y =0
a1
a2
a1
xy p ( x) p ( y) xp ( x) yp ( y)
1
x = 0 y =0
a1
a2
y p2 ( y )
y =0
E ( xy ) =
x =0
x p1 ( x)
x =0
6.44
a2
a1
y =0
x p1 ( x)
x =0
a2
y p ( y) = 0
2
y =0
xy e x e y dx dy = xe x dx ye y dy = 12
0 0
Cov(x, y ) = E ( x, y ) 12 = 12 12 = 0
6.46
p1 ( x) =
1
for x = 1, 2, , 6
6
and p2 ( y ) =
E ( x) =
1
,
36
1
for y = 1, 2, 3, , 6
6
xp ( x) = 1 6 + 2 6 + 3 6 + 4 6 + 5 6 + 6 6 = 3.5
1
x =1
E ( y) =
yp ( y) = 1 6 + 2 6 + 3 6 + 4 6 + 5 6 + 6 6 = 3.5
1
y =1
115
E ( x + y ) = E ( x) + E ( y ) = 3.5 + 3.5 = 7
V ( x + y ) = 12 + 22 + 2 Cov( x, y )
First, find 12 , 22 , Cov( x, y )
E( x2 ) =
1
1
1
1
1
1
p1 ( x) = 12 + 22 + 32 + 42 + 52 + 62
6
6
6
6
6
6
x =1
1 4 9 16 25 36 91
+ + + + +
= = 15.1667
6 6 6 6 6
6
6
E( y2 ) =
y =1
1
1
1
1
1
1
p2 ( y ) = 12 + 22 + 32 + 42 + 52 + 62
6
6
6
6
6
6
=
1 4 9 16 25 36 91
+ + + + +
= = 15.1667
6 6 6 6 6
6
6
Cov( x, y ) = E ( xy ) E ( x) E ( y )
E ( xy ) =
xy p( x, y) = 1(1) 36 + 1(2) 36 +
1
x =1 y =1
1 441
+ 6(6) =
= 12.25
36 36
f(x, y) = ce x , 0 y x <
1= c
x
0
e x dydx = c
e x y dx = c
0
2
e x2
= c
2
c=2
xe x dx
1 c
= c 0 =
2 2
f(x, y) = 2e x , 0 y x <
116
Chapter 6
E ( x y) = 2
( x y )e x dydx = 2
2 y2
x
x2
x
xe y e
0
2
=2
= (0 0) +
1
2
xe x dy
x
0
ye x dy dx
dx
0
x 2 e x
dx =
2
x 2 e x dx
ex
dx
2
e x
2 x 2e x x2
dx = 2
2
xe x
=
2
Let
e x dx =
1 1
2 2
4
u=x
2
dv = xe x dx
du = dx
e x
v=
2
e ax dx =
1
2 a
=2
=2
=
2 x2
x e
y 2 xe
x2
y2
2
+e
x2
e x
2
2 xe x
dx = 0 +
x
0
x 2 e x dy 2
x
0
xye x dy +
x
0
y 2 e x dy dx
dx
0
x
y3
3
2
2
x3 2
2 x 3e x x3e x + e x dx = 2
3
x 2 e x
2
=
( x 2 2 xy + y 2 )e x dydx = 2
x3 x2
2
e dx =
3
3
x3e x dx
xe x dx
1 1
= 0 =
2 2
u = x2 du = 2xdx
117
dv = xe
x2
e x
dx y =
2
1
1 8
=
= =
2 4
2 16
16
6.50
6.52
y=
E(x) = 1p + 0 (1 p) = p
( x ) = E ( x) = p = np
a.
E(y) = E
b.
p = es
( y ) = np = nes
5
y
2 for 0 < y < 5, which 0 < a < 2
Let a =
2 y 5 for 5 < y < 10, which implies 5 < a < 15
2
2
2
y0 = 2a0 for 0 < a0 <
y0 =
2a0 + 5
5
15
for < a0 <
2
2
2
2 a0
F ( y0 ) = F (2a0 ) =
for
2a
0
1
1
2
1
dy = y = a0 = a0
10
10
10
5
0
5
2
2a + 5
F ( y0 ) = F 0
=
2
2 a0 +5
2
5
2
2 a0 +5
2
1
1
dy = y
10
10
5
2a0 + 5 5
1
= a
20
20 10
5
15
< a0 <
2
2
1
dF (a ) 5
f (a) =
=
da
1
10
118
5
2
5
2
5
15
<a<
2
2
0<a<
Chapter 6
6.56
P ( w w0 ) =
w0 x
e dydx +
w0 x w0
dydx
0 0
w0
dx + e x y dx
= e x y
0
w0
0
xw0
w0
e x ( x x + w0 )dx + e x ( x 0 ) dx
w0
w0e x dx +
w0
w0
xe
dx
w0
0
= w0e x + xe x + e x dx
0
w0
w0
w0
= w0e x xe x e x
w0
0
0
) (
) (
= 0 + w0e w0 w0e w0 0 e w0 1 = 1 e w0
F ( w) = 1 e w
f ( w) =
6.58
dF ( w)
= e w
dw
E ( ) = E [ 3 y1 + 2 y2 + 6 y3 y4 ]
= 3E ( y1 ) + 2 E ( y2 ) + 6 E ( y3 ) E ( y4 )
= 3(2) + 2(4) + 6(1) 0 = 4
V ( ) = V [ 3 y1 + 2 y2 + 6 y3 y4 ]
119
6.60
a.
Let w = e y
ln w0
F ( y0 ) = F ( ln w0 ) =
( y 3)
dy = e e
0
3 y
b.
dF ( w)
= e3
dw
P ( w w0 ) = G ( w0 ) = F ( y0 ) = P ( y y0 ). This implies y0 = w0 + 3
w0 +3
F ( y0 ) = F ( w0 + 3) =
( y 3)
( )
dy = e e
w +3
w +3
= e3 e ( 0 ) 1 = e w0 + e3
F ( w) = e w + e3
f ( w) =
c.
Let w =
dF ( w)
= e w
dw
y
3
. The range for y is y > 3, which implies w > or w > 1.
3
3
F ( y0 ) = F (3w0 ) =
( y 3)
( )
dy = e e
3 w0
= e3 e3w0 e1 = e 3( w0 1) + e 2
F ( w) = e 3( w1) + e 2
f ( w) =
120
dF ( w)
= 3e 3( w1)
dw
Chapter 6
6.66
a.
The Central Limit Theorem states that the sampling distribution of y is approximately
normally distributed with a mean of y = = 0.53 and
y =
= 0.193
50
= 0.02729 .
b.
0.58 0.53
c.
Before tensioning:
0.59 0.53
After tensioning:
0.59 0.58
Handrubbing
y = = 35 , y =
59
= 8.344
50
30 35
y = = 69 , y =
106
= 14.991
50
30 69
121
6.70
P( y 400.8) = P z
= P(z 3.09) = .5 .4990 = .0010
1.6833
6.72
a.
b.
Since the probability, given = 1,700, is almost 0, we would cast doubt on the value of
1700 for the mean. In fact, we would believe that > 1,700.
45
6.74
i =1
with mean
yi
yi
n 2 = 45(55) 2
= 368.95122.
45
y 10,000 = P z
i
i =1
10,000 9,000
368.95122
a.
sampling distribution of
i =1
xi
= n = n and
122
yn
has an approximately standard normal distribution.
2n
Chapter 6
b.
Let Y = the number of the 50 college engineering graduates who believe that job matches
closely their engineering studies. Then Y has a binomial probability distribution with n = 50
and p = .30.
a.
P (Y 10) P Z <
= P ( Z 1.39) = 0.5000 0.4177 = 0.0823
3.2404
b.
24.5 15
P (Y 25) P Z >
= P( Z > 2.93) = 0.5000 0.4983 = 0.0017
3.2404
c.
30.5 15
19.5 15
Z
P (20 Y 30) P
3.2404
3.2404
= P(1.39 Z 4.78) 0.5000 0.4177 = 0.0823
6.80
Let y = the number of the twenty swordfish pieces with a level of mercury above the FDA
limit. Then y is a binomial random variable with n = 20 and p = .4.
a.
P ( y < 2) P z <
= P ( z < 2.97) = .5 P(2.97 < z < 0)
2.19
= .5 .4985 = .0015
b.
c.
10.5 8
= .5 .3729 = .1271
P ( y < 2) = P( y 1) = .0005
P ( y > 10) = 1 P ( y 10) = 1 .8725 = .1275
The normal approximation provides a good estimate of the binomial distribution.
123
6.82
Let Y = the number of the 70 major Denver bridges that have inspection ratings of 4 or below.
Then Y has a binomial probability distribution with n = 70 and p = .09.
a.
P (Y 35) P Z >
= P( Z > 11.78) 0
2.3944
b.
6.84
Let y = the number of the 500 drywall installers that are women. Then y has a binomial
probability distribution with n = 500 and p = .01.
a.
b.
6.86
Because the probability of observing such an outcome is so small, we would infer that
the 9% forecast is too low.
5.5 5
P ( y 5) P z
= P ( z .22) = .5 + P (0 z .22)
2.225
= .5 + .0871 = .5871
6.88
(n 1) s 2
a.
(10 1)14.4
2
P s 2 > 14.4 = P 2 >
= P > 14.4 ) .100
9
b.
(10 1)33.3
2
P s 2 > 33.3 = P 2 >
= P > 33.3 < .005
9
c.
(10 1)16.7
2
P s 2 > 16.7 = P 2 >
= P > 16.7 .050
9
a.
(
(
b.
1 = 9 degrees of freedom.
124
( n 1) s 2
(10 1)16.92
2
P ( s 2 < 16.92) = P 2 <
= P( < 1.5228) < .005
100
Chapter 6
c.
(10 1)98.158
2
P s 2 > 98.158 = P 2 >
= P > 8.83424 > .100
100
(n1 1) s12
2
1
(n2 1) s22
22
(n1 1) s12
F=
/(n1 1)
s12 12
=
2 2
(n2 1) s22
s2 2
/(
n
1)
2
2
12
Let A =
( y1 y2 ) ( 1 2 )
1 1
+
n1 n2
Let B = (n1 + n2 2) s /
2
Let t =
A
B /(n1 + n2 2)
( y1 y2 ) ( 1 2 )
1 1
+
n1 n2
2
=
(n1 + n2 2) s 2 / 2
(n1 + n2 2)
( y1 y2 ) ( 1 2 )
1 1
s2 +
n1 n2
( y1 y2 ) ( 1 2 )
1 1
+ s2 / 2
n
1 n2
( y1 y2 ) ( 1 2 )
1 1
s +
n1 n2
125
But t =
z
2 /
6.94
a.
To find the marginal probability distribution for x, we need to find P(x = 0),
P(x = 10), , P(x = 90). Since x = 0 can occur when y = 1, 2, 3, 4, or 5 occurs, then
P(x = 0) = p1 (0) is calculated by summing the probabilities of 5 mutually exclusive
events:
P(x = 0) = p1 (0) = p(0, 1) + p (0, 2) + p (0, 3) + p(0, 4) + p(0, 5)
= .001 + .005 + 0 + 0 + 0 = .006
Similarly,
P(x = 10) = p1 (10) = p (10, 1) +
+ p(10, 5) = .002 +
+ .002 = .010
+ 0 = .056
x
p1 ( x)
1
2
3
4
5
.105 .405 .355 .058 .077
p ( x, y )
p2 ( y )
Since there are 5 levels of y, there are 5 conditional probability distributions for x.
When y = 1, p1 ( x |1) =
p1 (0 |1) =
p1 (10 |1) =
126
p ( x, 1)
p2 (1)
p (0, 1) .001
=
= .0095
p2 (1) .105
p(10, 1) .002
=
= .0190
p2 (1)
.105
Chapter 6
p1 (20 |1) =
p (20, 1) .002
=
= .0190
p2 (1)
.105
p1 (90 |1) =
p (90, 1)
0
=
=0
p2 (1)
.105
0
10
20
30
40
50
60
70
80 90
.0095 .0190 .0190 .2381 .3810 .2381 .0476 .0476 0 0
The other conditional distributions are found in a similar manner and appear below:
0
10
20
30
40
50
60
70
80
90
.0123 .0123 .0247 .1852 .2469 .1852 .1234 .0741 .0741 .0617
x
p1 ( x | 2)
x
p1 ( x | 3)
0 10 20
30
40
50
60
70
80
90
0 0 0 .0704 .1408 .2254 .1408 .2254 .1127 .0845
x
p1 ( x | 4)
0
10
20
30
40
50
60
70
80
90
0 .0172 .0345 .0862 .1724 .4310 .1724 .0517 .0172 .0172
x
p1 ( x | 5)
0
10
20
30
40
50
60
70 80 90
0 .0260 .0649 .0649 .2597 .3896 .1948 0 0 0
c.
Find
d.
E ( y) =
P ( x 40 | y = 3)
= p1 (40 | 3) + p1 (50 | 3) + p1 (60 | 3) + p1 (70 | 3) + p1 (80 | 3) + p1 (90 | 3)
= .1408 + .2254 + .1408 + .2254 + .1127 + .0845 = .9296
5
y =1
e.
f.
variance = $457,124
127
6.96
a.
5
=
= 1.118
y = = 15 and y =
n
20
b.
z=
y x
6 15
= 7.42
1.118
P ( y 6) = P( z .742)
= .5 P (7.42 z 0)
.5 .5 (from Table 5, Appendix B)
=0
6.98
c.
Since we should not see this type of result if = 15, we believe the mean time to fall
asleep for the men taking melatonin is less than 15 minutes.
a.
b.
P ( y = 20 | x = .3) =
c.
E ( x) = .207
E ( y ) = 10.0
E ( xy ) = 1.76
Cov( xy ) = E ( xy ) E ( x) E ( y ) = 1.76 (.207)(10) = .31
x and y are correlated.
6.100
d.
a.
y = = .000005
y = / n = .000002 / 50 = .00000028
b.
.00000028
128
Chapter 6
6.102
( n 1) s 2
freedom.
(32 1)(1,311)
2
P ( s 2 > 1,311) = P 2 >
= P > 53.66
2
(27.52)
< .005
6.104
The number of defectives, y, in the sample of 200 has a binomial distribution with n = 200
and p = .08. The lot will be rejected if more than 6% (12/200) of the sample proves to be
defective.
(12 + .5) np
P(lot rejected) = P ( y > 12) P z >
npq
(12.5 200(.08)
= P z >
= P ( z > .091)
200(.08)(.92)
6.106
a.
b.
1, 418 1,312
P ( y 1, 418) = P z
= P( z 2.51)
42.2
c.
If the actual mean is y = 1.418, we would believe the population average stated,
= 1,312, is incorrect.
d.
(n 1) s 2
degrees of freedom.
e.
(100 1)250,000
2
P ( s 2 > 5002 ) = P 2 >
= P ( > 138.979)
4222
Using Table 8, Appendix B, this probability is between .005 and .01. Since
.005 < P( s 2 > 5002 ) < .01, then .005 < P ( s > 500) < .01.
6.108
a.
2
n
602
= 36
100
129
b.
c.
6.110
Because the sample size is fairly large, the Central Limit Theorem says that the
sampling distribution of is approximately normal.
30 60
= P(z 5.0) .5 .5 = 0
P( y 30) = P z
36
Let c = (2 y 2 + 3). The range of the y is 1 y 5 which implies the range of the c is
5 c 53.
P (c c0 ) = C (c0 ) = F ( y0 ) = P ( y y0 ). This implies that y0 =
c3
F ( y0 ) = F
=
2
( c 3) / 2
F (c ) =
1 c 3 1
4
2
4
f (c ) =
1
dF (c)
(c 3) 2
=
dc
8 2
1
1
dy = y
4
4
1
( c 3) / 2
c3
2
1 c3 1
4
2
4
20
P (c 20) = 1 P (c 20) = 1
8
5
1 c3
= 1
4
2
20
1
2
(c 3) 2 dc
1 17
2
= 1
4 2
2
= 1 .4789 = .5211
6.112
a.
V ( x + y ) = V ( x) + V ( y ) + 2(1)(1)Cov( x, y ) = V ( x) + V ( y ) + 0 = V ( x) + V ( y )
V ( x y ) = V ( x) + V ( y ) + 2(1)(1)Cov( x, y ) = V ( x) + V ( y ) + 0 = V ( x) + V ( y )
V ( x + y) = V ( x y)
b.
130
Cov [ ( x + y ), ( x y )]
= (1)(1)Cov( x, x) + (1)(1)Cov( y, x) + (1)(1)Cov( x, y ) + (1)(1)Cov( y, y )
= Cov( x, x) + Cov( x, y ) Cov( x, y ) Cov( y , y )
= Var(x) Var(y)
Chapter 6
6.114
a.
0 w 1 or 0 w 1.
F ( y0 ) = F
( )
w02
w2
0
3 y 2 dy = y 3 = w06 0 = w06
0
F ( w) = w06
f ( w) =
b.
dF ( w)
= 6 w05
dw
P( w w0 ) = w( w0 ) = F ( y0 ) = P( y y0 ). This implies y0 = w0 3.
F ( y0 ) = F ( w0 3) =
w0 3
w 3
0
3 y 2 dy = y 3
0
= ( w0 3) 0 = ( w0 3)
3
F ( w) = ( w 3)3
f ( w) =
c.
dF ( w)
= 3( w 3) 2
dw
P ( w w0 ) = w( w0 ) = F ( y0 ) = P ( y y0 ). This implies y0 = e w0 .
F ( y0 ) = F e
w0
w0
) = 3 y dy = y
2
w0
3 e
= e w0
0 = e3w0
F ( w) = e 3 w
f ( w) =
6.116
dF ( w)
= 3e 3 w
dw
E ( w) = 2 / E ( y ) = 2 / = 2
131
e y /
f ( y) =
0
e w / 2
f ( w) =
0
1 w/ 2
e
f ( w) =
0
0 y
elsewhere
0w
elsewhere
0w
elsewhere
To use Theorem 6.7, we must first find the cumulative distribution function of y.
y
F ( y ) = 2(t 1)dt = t 2 2t 1 = y 2 2 y (1 2) = ( y 1) 2
1
Let g = F ( y ) = ( y 1) 2 . By Theorem 6.7, g has a uniform density function over the interval
0 g 1.
g = ( y 1) 2 g = ( y 1) y = 1 + g
By selecting random numbers from the random number table and substituting them in for g,
we will get random selections for y.
6.122
(ln y ) 2
1
e 2
f ( y ) = y 2
x = ln y dx =
y>0
otherwise
1
dy, < x <
y
1
Thus, by substitution, f ( x) =
e
2
( x )2
2 2
< x <
132
Chapter 6