CH 10

Applied Statistics and Probability for Engineers, 5
th
edition December 20, 2010
10-1
CHAPTER 10

Section 10-2

10-1 a) 1) The parameter of interest is the difference in means
1 2
. Note that A
0
= 0.
2) H
0
: 0
2 1
= or
2 1
=
3) H
1
: 0
2 1
= or
2 1
=
4) The test statistic is
z
x x
n n
0
1 2 0
1
2
1
2
2
2
=

+
( ) A
o o

5) Reject H
0
if z
0
< z
o/2
= 1.96 or z
0
> z
o/2
= 1.96 for o = 0.05
6) x
1
= 4.7 x
2
= 7.8
o
1
= 10 o
2
= 5
n
1
= 10 n
2
= 15

9 . 0
15
) 5 (
10
) 10 (
) 8 . 7 7 . 4 (
2 2
0
=
+
= z

7) Conclusion: Because 1.96 < 0.9 < 1.96, do not reject the null hypothesis. There is not sufficient evidence to
conclude that the two means differ at o = 0.05.

P-value = 368 . 0 ) 815950 . 0 1 ( 2 )) 9 . 0 ( 1 ( 2 = = u

b) ( ) ( ) x x z
n n
x x z
n n
1 2 2
1
2
1
2
2
2
1 2 1 2 2
1
2
1
2
2
2
+ s s + +
o o
o o

o o
/ /

( ) ( )
15
) 5 (
10
) 10 (
96 . 1 8 . 7 7 . 4
15
) 5 (
10
) 10 (
96 . 1 8 . 7 7 . 4
2 2
2 1
2 2
+ + s s +

59 . 3 79 . 9
2 1
s s

With 95% confidence, the true difference in the means is between 9.79 and 3.59. Because zero is contained in this
interval, we conclude there is no significant difference between the means. We fail to reject the null hypothesis.

c)

|
|
|
|
|
.
|
\
|
+
A A
u
|
|
|
|
|
.
|
\
|
+
A A
u =
2
2
2
1
2
1
0
2 /
2
2
2
1
2
1
0
2 /
n n
z
n n
z
o o o o
|
o o

=
|
|
|
|
|
.
|
\
|
+
u
|
|
|
|
|
.
|
\
|
+
u
15
) 5 (
10
) 10 (
3
96 . 1
15
) 5 (
10
) 10 (
3
96 . 1
2 2 2 2

=
( ) ( ) 83 . 2 08 . 1 u u
= 0.8599 0.0023 = 0.86
Power = 1 0.86 = 0.14

d) Assume the sample sizes are to be equal, use o = 0.05, | = 0.05, and o = 3

( ) ( ) ( ) ( )
5 . 180
) 3 (
5 10 645 . 1 96 . 1
2
2 2 2
2
2
2
2
1
2
2 /
=
+ +
=
+ +
~
o
o o
| o
z z
n

Use n
1
= n
2
= 181

th
10-2
10-3 a) 1) The parameter of interest is the difference in means
1 2
. Note that A
0
= 0.
2) H
0
: 0
2 1
= or
2 1
=
3) H
1
: 0
2 1
> or
2 1
>
z
x x
n n
0
1 2 0
1
2
1
2
2
2
=

+
( ) A
o o

5) Reject H
0
if z
0
> z
o
=2.325 for o = 0.01
6) x
1
= 24.5 x
2
= 21.3
o
1
= 10 o
2
= 5
n
1
= 10 n
2
= 15

937 . 0
15
) 5 (
10
) 10 (
) 3 . 21 5 . 24 (
2 2
0
=
+
= z

7) Conclusion: Because 0.937 < 2.325, we fail to reject the null hypothesis. There is not sufficient evidence to
conclude that the two means differ at o = 0.01.

P-value = 1- 1736 . 0 8264 . 0 1 ) 94 . 0 ( = = u

b) ( )
2
2
2
1
2
1
2 1 2 1
n n
z x x
o o

o
+ >

( )
15
) 5 (
10
) 10 (
325 . 2 3 . 21 5 . 24
2 2
2 1
+ >

74 . 4
2 1
>

The true difference in the means is greater than -4.74 with 99% confidence. Because zero is contained in this interval,
we fail to reject the null hypothesis.

c)

|
|
|
|
|
.
|
\
|
+
u =
2
2
2
1
2
1
n n
z
o o
o
|
o
=
|
|
|
|
|
.
|
\
|
+
u
15
) 5 (
10
) 10 (
2
325 . 2
2 2

=
( ) 74 . 1 u
= 0.959
Power = 1 0.96 = 0.04

d) Assume the sample sizes are to be equal, use o = 0.05, | = 0.05, and A = 3

( ) ( ) ( ) ( )
339
) 2 (
5 10 645 . 1 645 . 1
2
2 2 2
2
2
2
2
1
2
=
+ +
=
+ +
~
o
o o
| o
z z
n

Use n
1
= n
2
= 339

10-5 a) 1) The parameter of interest is the difference in breaking strengths
1 2
and A
0
= 10
2) H
0
:
1 2
10 =
3) H
1
:
1 2
10 >
th
10-3

5) Reject H
0
if z
0
> z
o
= 1.645 for o = 0.05
6) x
1
= 162.5 x
2
= 155.0 o = 10
o
1
= 1.0 o
2
= 1.0
n
1
= 10 n
2
= 12
z
0
2 2
162 5 1550 10
10
10
10
12
584 =

+
=
( . . )
( . ) ( . )
.
7) Conclusion: Because 5.84 < 1.645 fail to reject the null hypothesis. There is insufficient evidence to support the use
of plastic 1 at o = 0.05.

P-value=
( ) 84 . 5 1 u
= 1-0=1

b) ( )
2
2
2
1
2
1
2 1 2 1
n n
z x x
o o

o
+ >

( )
12
) 1 (
10
) 1 (
645 . 1 155 5 . 162
2 2
2 1
+ >

8 . 6
2 1
>

c) | =
( ) 0012 . 0 03 . 3
12
1
10
1
) 10 12 (
645 . 1 = u =
|
|
|
|
.
|
\
|
+
u

Power = 1 0.0012 = 0.9988
d)

6 42 . 5
) 10 12 (
) 1 1 ( ) 645 . 1 645 . 1 (
) (
) ( ) (
2
2
2
0
2
2
2
1
2
2
~ =
+ +
=
A A
+ +
=
o o
| o
z z
n

Yes, the sample size is adequate

10-7 x
1
= 89.6 x
2
= 92.5
o
1
2
= 1.5 o
2
2
= 1.2
n
1
= 15 n
2
= 20

a) 1) The parameter of interest is the difference in mean road octane number
1 2
and A
0
= 0
2) H
0
:
1 2
0 = or
1 2
=
3) H
1
:
1 2
0 < or
1 2
<

2
2
2
1
2
1
0 2 1
0
) (
n n
x x
z
o o
+
A
=

5) Reject H
0
if z
0
< z
o
= 1.645 for o = 0.05
6) x
1
= 89.6 x
2
= 92.5
o
1
2
= 1.5 o
2
2
= 1.2
n
1
= 15 n
2
= 20

th
10-4

25 . 7
20
2 . 1
15
5 . 1
) 5 . 92 6 . 89 (
0
=
+
= z

7) Conclusion: Because 7.25 < 1.645 reject the null hypothesis and conclude the mean road octane number for
formulation 2 exceeds that of formulation 1 using o = 0.05.

P-value ~ 0 1 1 ) 25 . 7 ( 1 ) 25 . 7 ( ~ = s = s z P z P

b) 95% confidence interval:
( ) ( ) x x z
n n
x x z
n n
1 2 2
1
2
1
2
2
2
1 2 1 2 2
1
2
1
2
2
2
+ s s + +
o o
o o

o o
/ /

( ) ( . . ) .
. .
. . .
. .
89 6 925 196
15
15
12
20
89 6 925 196
15
15
12
20
1 2
+ s s + +
s s 3684 2116
1 2
. .

With 95% confidence, the mean road octane number for formulation 2 exceeds that of formulation 1 by between 2.116
and 3.684.

c) 95% level of confidence, E = 1, and z
0.025
=1.96

( ) , 37 . 10 ) 2 . 1 5 . 1 (
1
96 . 1
2
2
2
2
1
2
025 . 0
= + |
.
|
\
|
= + |
.
|
\
|
~ o o
E
z
n

Use n
1
= n
2
= 11

10-9 Catalyst 1 Catalyst 2
x
1
= 65.22 x
2
= 68.42
o
1
= 3 o
2
= 3
n
1
= 10 n
2
= 10

a) 95% confidence interval on
1 2
, the difference in mean active concentration
( ) ( ) x x z
n n
x x z
n n
1 2 2
1
2
1
2
2
2
1 2 1 2 2
1
2
1
2
2
2
+ s s + +
o o
o o

o o
/ /

( ) ( . . ) .
( ) ( )
. . .
( ) ( )
6522 6842 196
3
10
3
10
6522 6842 196
3
10
3
10
2 2
1 2
2 2
+ s s + +
s s 583 057
1 2
. .

We are 95% confident that the mean active concentration of catalyst 2 exceeds that of catalyst 1 by between 0.57 and
5.83 g/l.

P-value:
38 . 2
10
3
10
3
) 42 . 68 22 . 65 ( ) (
2 2
2
2
2
1
2
1
0 2 1
0
=
+
=
+
A
=
n n
x x
z
o o

Then P-value = 2(0.008656) = 0.0173

b) Yes, because the 95% confidence interval does not contain the value zero. We conclude that the mean active
concentration depends on the choice of catalyst.

c)
th
10-5

( ) ( )
038364 . 0
0 038364 . 0 69 . 5 77 . 1
10
3
10
3
) 5 (
96 . 1
10
3
10
3
) 5 (
96 . 1
2 2 2 2
=
= u u =
|
|
|
|
|
.
|
\
|
+
u
|
|
|
|
|
.
|
\
|
+
u = |

Power = 1 | = 1 0.038364 = 0.9616.

d) Calculate the value of n using o and |.

( ) ( )
( )
( )
, 02 . 10
) 5 (
) 9 9 ( 77 . 1 96 . 1
2
2
2
0
2
2
2
1
2
2 /
=
+ +
=
A A
+ +
~
o o
| o
z z
n

Therefore, 10 is only slightly too few samples. The sample sizes are adequate to detect the difference of 5.

The data from the first sample n = 15 appear to be normally distributed.
700 750 800
1
5
10
20
30
40
50
60
70
80
90
95
99
P
e
r
c
e
n
t

The data from the second sample n = 8 appear to be normally distributed
700 750 800
1
5
10
20
30
40
50
60
70
80
90
95
99
P
e
r
c
e
n
t

Plots for both samples are shown in the following figure.
th
10-6

55 65 75
1
5
10
20
30
40
50
60
70
80
90
95
99
P
e
r
c
e
n
t

Section 10-2

10-11 a) =
1
x 54.73 x
2
= 58.64 s
1
2
= 2.13
2
s
2
2
= 5.28
2
n
1
= 15 n
2
= 20

26 45 . 26
1 20
)
20
28 . 5
(
1 15
)
15
13 . 2
(
)
20
28 . 5
15
13 . 2
(
1
) (
1
) (
) (
2
2
2
2
2
2 2
2
2
2
2
2
1
2
1
2
1
2
2
2
2
1
2
1
~ =
+
=
+
=
n
n
s
n
n
s
n
s
n
s
v
(truncated)

The 95% upper one-sided confidence interval:
706 . 1
26 , 05 . 0
= t

( )
2
2
2
1
2
1
, 2 1 2 1
n
s
n
s
t x x + + s
v o

( )
( ) ( )
20
28 . 5
15
13 . 2
706 . 1 64 . 58 74 . 54
2 2
2 1
+ + s

6880 . 1
2 1
s

P-value = P(t < 3.00): 0.0025 < P-value < 0.005

This is one-sided test because the hypotheses are mu1 mu2 = 0 versus less than 0.

b) Because 0.0025 < P-value < 0.005 the P-value < o = 0.05. Therefore, we reject the null hypothesis of mu1 mu2 =
0 at the 0.05 or the 0.01 level of significance.

c) Yes, the sample standard deviations are quite different. Consequently, one would not want to assume that the
population variances are equal.

d) If the alternative hypothesis were changed to mu1 mu2 0, then the P-value = 2P (t < 3.00) and 0.005 < P-value
< 0.01. Because the P-value < o = 0.05, we reject the null hypothesis of mu1 mu2 = 0 at the 0.05 level of
significance.

th
10-7
10-13 a) 1) The parameter of interest is the difference in means,
1 2
, with A
0
= 0
2) H
0
:
1 2
0 = or
1 2
=
3) H
1
:
1 2
0 < or
1 2
<
t
x x
s
n n
p
0
1 2 0
1 2
1 1
=

+
( ) A

5) Reject the null hypothesis if t
0
<
+
t
n n o,
1 2
2
where t
0 05 28 . ,
= 1.701 for o = 0.05
6)
x
1
= 6.2 x
2
= 7.8
s
n s n s
n n
p
=
+
+
( ) ( )
1 1
2
2 2
2
1 2
1 1
2

s
1
2
= 4 s
2
2
= 6.25 26 . 2
28
) 25 . 6 ( 14 ) 4 ( 14
=
+
=
n
1
= 15 n
2
= 15

94 . 1
15
1
15
1
26 . 2
) 8 . 7 2 . 6 (
0
=
+
= t

7) Conclusion: Because -1.94 < 1.701 reject the null hypothesis at the 0.05 level of significance.

P-value = P ( ) 94 . 1 > t 0.025 < P-value < 0.05

b) 95% confidence interval: t
0 05 28 . ,
= 1.701
( )
2 1
2 , 2 1 2 1
1 1
) (
2 1
n n
s t x x
p n n
+ + s
+ o

15
1
15
1
) 26 . 2 ( 701 . 1 ) 8 . 7 2 . 6 (
2 1
+ + s
196 . 0
2 1
s

Because zero is not contained in this interval, we reject the null hypothesis.

c) 3 = A Use s
p
as an estimate of o:
d = 66 . 0
) 26 . 2 ( 2
3
2
1 2
= =
p
s

Using Chart VII (g) with d = 0.66 and
2 1
n n n = = we get n
*
= 2n - 1 =29 and = 0.05 . Therefore, | = 0.05 and the
power is 1-| = 0.95

d) | = 0.05, d =
) 26 . 2 ( 2
5 . 2
= 0.55. Therefore n
*
~ 40 and
2
1 + -
=
n
n ~ 21. Thus,
2 1
n n n = = =21

10-15 a) 1) The parameter of interest is the difference in mean rod diameter,
1 2

2) H
0
:
1 2
0 = or
1 2
=
3) H
1
:
1 2
0 = or
1 2
=
th
10-8

0
< where = 2.042 or t
0
> t
n n o/ , 2 2
1 2
+
where
t
0 025 30 . ,
= 2.042 for o = 0.05
6) x
1
= 8.73 x
2
= 8.68
s
1
2
= 0.35 s
2
2
= 0.40 =
+
=
14 035 16 040
30
0614
( . ) ( . )
.
n
1
= 15 n
2
= 17

230 . 0
17
1
15
1
614 . 0
) 68 . 8 73 . 8 (
0
=
+
= t

7) Conclusion: Because 2.042 < 0.230 < 2.042, fail to reject the null hypothesis. There is insufficient evidence to
conclude that the two machines produce different mean diameters at o = 0.05.

P-value = 2P ( ) t > > 0230 . 2(0.40), P-value > 0.80

0.025,30
= 2.042
( ) ( ) x x t s
n n
x x t s
n n
n n p n n p 1 2 2 2
1 2
1 2 1 2 2 2
1 2
1 2 1 2
1 1 1 1
+ s s + +
+ + o o

/ , / ,
( ) ( )
( ) ( . . ) . ( . ) . . . ( . ) 873 868 2 042 0614
1
15
1
17
873 868 2 042 0643
1
15
1
17
1 2
+ s s + +
494 . 0 394 . 0
2 1
s s
Because zero is contained in this interval, there is insufficient evidence to conclude that the two machines produce rods
with different mean diameters.
10-17 a) 1) The parameter of interest is the difference in mean catalyst yield,
1 2
, with A
0
= 0
2) H
0
:
1 2
0 = or
1 2
=
3) H
1
:
1 2
0 < or
1 2
<
t
x x
s
n n
p
0
1 2 0
1 2
1 1
=

+
( ) A

0
<
+
t
n n o,
1 2
2
where
25 , 01 . 0
t = 2.485 for o = 0.01
6) x
1
= 86 x
2
= 89 s
n s n s
n n
p
=
+
+
( ) ( )
1 1
2
2 2
2
1 2
1 1
2

s
1
= 3 s
2
= 2
4899 . 2
25
) 2 ( 14 ) 3 ( 11
2 2
=
+
=

n
1
= 12 n
2
= 15

11 . 3
15
1
12
1
4899 . 2
) 89 86 (
0
=
+
= t

7) Conclusion: Because 3.11 < 2.485, reject the null hypothesis and conclude that the mean yield of catalyst 2
exceeds that of catalyst 1 at o = 0.01.

b) 99% upper confidence interval
2 1
: t
0.01,25
= 2.485
th
10-9

( )
2 1
2 , 2 / 2 1 2 1
1 1
) (
2 1
n n
s t x x
p n n
+ + s
+ o

( )
15
1
12
1
) 4899 . 2 ( 485 . 2 89 86
2 1
+ + s

603 . 0
2 1
s
or equivalently
2 1
603 . 0 s +

We are 99% confident that the mean yield of catalyst 2 exceeds that of catalyst 1 by at least 0.603 units.

10-19
a) According to the normal probability plots, the assumption of normality appears to reasonable because the data from
both the samples fall approximately along a straight line. The equality of variances does not appear to be severely
violated either because the slopes are approximately the same for both samples.

P-Value: 0.595
A-Squared: 0.269
Anderson-Darling Normality Test
N: 10
StDev : 0.421769
Av erage: 9.97
10. 5 10. 0 9. 5
. 999
. 99
. 95
. 80
. 50
. 20
. 05
. 01
. 001
P
r
o
b
a
b
i
l
i
t
y
solution
Normal Probability Plot
P-Value: 0.804
A-Squared: 0.211
N: 10
StDev : 0.230940
Av erage: 10.4
10. 7 10. 6 10. 5 10. 4 10. 3 10. 2 10. 1 10. 0
. 999
. 99
. 95
. 80
. 50
. 20
. 05
. 01
. 001
P
r
o
b
a
b
i
l
i
t
y
solution

b) 1) The parameter of interest is the difference in mean etch rate,
1 2
, with A
0
= 0
2) H
0
:
1 2
0 = or
1 2
=
3) H
1
:
1 2
0 = or
1 2
=
t
x x
s
n n
p
0
1 2 0
1 2
1 1
=

+
( ) A

0
<
+
t
n n o/ , 2 2
1 2
where t
0 025 18 . ,
= 2.101 or t
0
> t
n n o/ , 2 2
1 2
+
where
t
0 025 18 . ,
= 2.101 for o = 0.05
6) x
1
= 9.97 x
2
= 10.4 s
n s n s
n n
p
=
+
+
( ) ( )
1 1
2
2 2
2
1 2
1 1
2

s
1
= 0.422 s
2
= 0.231 340 . 0
18
) 231 . 0 ( 9 ) 422 . 0 ( 9
2 2
=
+
=
n
1
= 10 n
2
= 10
83 . 2
10
1
10
1
340 . 0
) 4 . 10 97 . 9 (
0
=
+
= t
7) Conclusion: Because 2.83 < 2.101 reject the null hypothesis and conclude the two machines mean etch rates
differ at o = 0.05.

P-value = 2P ( ) 83 . 2 < t 2(0.005) < P-value < 2(0.010) = 0.010 < P-value < 0.020

th
10-10
c) 95% confidence interval: t
0.025,18
= 2.101
( ) ( ) x x t s
n n
x x t s
n n
n n p n n p 1 2 2 2
1 2
1 2 1 2 2 2
1 2
1 2 1 2
1 1 1 1
+ s s + +
+ + o o

/ , / ,
( ) ( )

( )
10
1
10
1
) 340 (. 101 . 2 4 . 10 97 . 9
10
1
10
1
) 340 (. 101 . 2 ) 4 . 10 97 . 9 (
2 1
+ + s s +

1105 . 0 7495 . 0
2 1
s s

We are 95% confident that the mean etch rate for solution 2 exceeds the mean etch rate for solution 1 by between 0.1105
and 0.7495.

10-21 a) 1) The parameter of interest is the difference in mean melting point,
1 2
, with A
0
= 0
2) H
0
:
1 2
0 = or
1 2
=
3) H
1
:
1 2
0 = or
1 2
=
t
x x
s
n n
p
0
1 2 0
1 2
1 1
=

+
( ) A

0
<
+
t
n n o/ , 2 2
1 2
where
40 , 0025 . 0
t = 2.021 or t
0
> t
n n o/ , 2 2
1 2
+
where
40 , 025 . 0
t = 2.021 for o = 0.05
6) x
1
= 420 x
2
= 426 s
n s n s
n n
p
=
+
+
( ) ( )
1 1
2
2 2
2
1 2
1 1
2

s
1
= 4 s
2
= 3
536 . 3
40
) 3 ( 20 ) 4 ( 20
2 2
=
+
=

n
1
= 21 n
2
= 21

498 . 5
21
1
21
1
536 . 3
) 426 420 (
0
=
+
= t

7) Conclusion: Because 5.498 < 2.021 reject the null hypothesis. The alloys differ significantly in mean melting
point at o = 0.05.

P-value = 2P ( ) 498 . 5 < t P-value < 0.0010
b) d =
| |
( )
.

o
1 2
2
3
2 4
0375
= =
Using the appropriate chart in the Appendix, with | = 0.10 and o = 0.05 we have n
*
= 75.
Therefore, n
n
=
+
=
*
1
2
38 , n
1
= n
2
=38

10-23 a) 1) The parameter of interest is the difference in mean wear amount,
1 2
, with A
0
= 0
. 2) H
0
:
1 2
0 = or
3) H
1
:
1 2
0 = or
1 2
=
t
x x
s
n
s
n
0
1 2 0
1
2
1
2
2
2
=

+
( ) A

0
<
26 , 025 . 0
t or t
0
>
26 , 025 . 0
t where
26 , 025 . 0
t = 2.056 for o = 0.05 because
th
10-11

26
98 . 26
1 1
2
2
2
2
1
2
1
2
1
2
2
2
2
1
2
1
~
=
|
|
.
|
\
|
+
|
|
.
|
\
|
|
|
.
|
\
|
+
=
v
v
n
n
s
n
n
s
n
s
n
s

(truncated)
6) x
1
= 20 x
2
= 15
s
1
= 2 s
2
= 8
n
1
= 25 n
2
= 25

03 . 3
25
) 8 (
25
) 2 (
) 15 20 (
2 2
0
=
+
= t

7) Conclusion: Because 3.03 > 2.056 reject the null hypothesis. The data support the claim that the two companies
produce material with significantly different wear at the 0.05 level of significance.

P-value = 2P(t > 3.03), 2(0.0025) < P-value < 2(0.005), 0.005 < P-value < 0.010

b) 1) The parameter of interest is the difference in mean wear amount,
1 2

2) H
0
:
1 2
0 =
3) H
1
:
1 2
0 >
4) The test statistic is t
x x
s
n
s
n
0
1 2 0
1
2
1
2
2
2
=

+
( ) A

0
> t
0 05 27 . ,
where
26 , 05 . 0
t = 1.706 for o = 0.05 since
6) x
1
= 20 x
2
= 15
s
1
= 2 s
2
= 8
n
1
= 25 n
2
= 25
03 . 3
25
) 8 (
25
) 2 (
) 15 20 (
2 2
0
=
+
= t

7) Conclusion: Because 3.03 > 1.706 reject the null hypothesis. The data support the claim that the material from
company 1 has a higher mean wear than the material from company 2 at a 0.05 level of significance.

c) For part (a) use a 95% two-sided confidence interval:
t
0.025,26
= 2.056
( ) ( ) x x t
s
n
s
n
x x t
s
n
s
n
1 2
1
2
1
2
2
2
1 2 1 2
1
2
1
2
2
2
+ s s + +
o v o v

, ,

( )
25
) 8 (
25
) 2 (
056 . 2 15 20
25
) 8 (
25
) 2 (
056 . 2 ) 15 20 (
2 2
2 1
2 2
+ + s s +

391 . 8 609 . 1
2 1
s s

For part (b) use a 95% lower one-sided confidence interval:

706 . 1
26 , 05 . 0
= t

( ) x x t
s
n
s
n
1 2
1
2
1
2
2
2
1 2
+ s
o v

,

th
10-12

( )
( ) ( )
2 1
2 2
25
8
25
2
706 . 1 15 20 s +

2 1
186 . 2 s

For part a) we are 95% confident the mean abrasive wear from company 1 exceeds the mean abrasive wear from
company 2 by between 1.609 and 8.391 mg/1000.

For part b) we are 95% confident the mean abrasive wear from company 1 exceeds the mean abrasive wear from
company 2 by at least 2.186 mg/1000.

10-25 a) 1) The parameter of interest is the difference in mean width of the backside chip-outs for the single spindle
saw process versus the dual spindle saw process ,
1 2

2) H
0
:
1 2
0 = or
1 2
=
3) H
1
:
1 2
0 = or
1 2
=

2 1
0 2 1
0
1 1
) (
n n
s
x x
t
p
+
A
=
0
<
2 , 2 /
2 1
+
n n
t
o
where
28 , 025 . 0
t = 2.048 or t
0
> t
n n o/ , 2 2
1 2
+
where

28 , 025 . 0
t = 2.048 for o = 0.05
6) x
1
= 66.385 x
2
= 45.278
2
) 1 ( ) 1 (
2 1
2
2 2
2
1 1
+
+
=
n n
s n s n
s
p

2 2
1
895 . 7 = s
2 2
2
612 . 8 = s 26 . 8
28
) 612 . 8 ( 14 ) 895 . 7 ( 14
2 2
=
+
=
n
1
= 15 n
2
= 15

00 . 7
15
1
15
1
26 . 8
) 278 . 45 385 . 66 (
0
=
+
= t

7) Conclusion: Because 7.00 > 2.048, we reject the null hypothesis at o = 0.05. P-value ~ 0

0.025,28
= 2.048
( ) ( )
2 1
2 , 2 / 2 1 2 1
2 1
2 , 2 / 2 1
1 1
) (
1 1
) (
2 1 2 1
n n
s t x x
n n
s t x x
p n n p n n
+ + s s +
+ + o o

15
1
15
1
) 26 . 8 ( 048 . 2 ) 278 . 45 385 . 66 (
15
1
15
1
) 26 . 8 ( 048 . 2 ) 278 . 45 385 . 66 (
2 1
+ + s s +

28 . 27 93 . 14
2 1
s s
Because zero is not contained in this interval, we reject the null hypothesis.

c) For | < 0.01 and d =
) 26 . 8 ( 2
15
= 0.91, with = 0.05 then using Chart VII (e) we find n
*
> 15. Then
8
2
1 15
=
+
> n

th
10-13

10-27 a) 1) The parameter of interest is the difference in mean number of periods in a sample of 200 trains for two
different levels of noise voltage, 100mv and 150mv

1 2
, with A
0
= 0
2) H
0
:
1 2
0 = or
1 2
=
3) H
1
: 0
2 1
> or
2 1
>
t
x x
s
n n
p
0
1 2 0
1 2
1 1
=

+
( ) A

0
>
2 ,
2 1
+n n
t
o
where
198 , 01 . 0
t = 2.326 for o = 0.01
6)
x
1
= 7.9 x
2
= 6.9
s
n s n s
n n
p
=
+
+
( ) ( )
1 1
2
2 2
2
1 2
1 1
2

=
1
s 2.6 =
2
s 2.4 5 . 2
198
) 4 . 2 ( 99 ) 6 . 2 ( 99
2 2
=
+
=
n
1
= 100 n
2
= 100

82 . 2
100
1
100
1
5 . 2
) 9 . 6 9 . 7 (
0
=
+
= t

7) Conclusion: Because 2.82 > 2.326 reject the null hypothesis at the 0.01 level of significance.

P-value = P ( ) 82 . 2 > t P-value ~ 0.0025

198 , 01 . 0
t = 2.326
( )
2 1
2 , 2 1 2 1
1 1
) (
2 1
n n
s t x x
p n n
+ >
+ o

178 . 0
2 1
>

Because zero is not contained in this interval we reject the null hypothesis.

10-29
a) The data appear to be normally distributed and the variances appear to be approximately equal. The slopes of the
lines on the normal probability plots are almost the same.
th
10-14
b)
1) The parameter of interest is the difference in mean overall distance,
1 2
, with A
0
= 0
2) H
0
:
1 2
0 = or
1 2
=
3) H
1
:
1 2
0 = or
1 2
=
t
x x
s
n n
p
0
1 2 0
1 2
1 1
=

+
( ) A

0
<
+
t
n n o/ , 2 2
1 2
or t
0
> t
n n o/ , 2 2
1 2
+
where
18 , 025 . 0
t = 2.101 for o = 0.05
6) x
1
= 275.7 x
2
= 265.3
s
n s n s
n n
p
=
+
+
( ) ( )
1 1
2
2 2
2
1 2
1 1
2

s
1
= 8.03 s
2
= 10.04
09 . 9
20
) 04 . 10 ( 9 ) 03 . 8 ( 9
2 2
=
+
=

n
1
= 10 n
2
= 10

558 . 2
10
1
10
1
09 . 9
) 3 . 265 7 . 275 (
0
=
+
= t

7) Conclusion: Because 2.558 > 2.101 reject the null hypothesis. The data support the claim that the means differ at o
= 0.05.

P-value = 2P ( ) 558 . 2 > t P-value ~ 2(0.01) = 0.02
c)
( ) ( )
2 1
, 2 1 2 1
2 1
, 2 1
1 1 1 1
n n
s t x x
n n
s t x x
p p
+ + s s +
v o v o

( )
10
1
10
1
) 09 . 9 ( 101 . 2 3 . 265 7 . 275
10
1
10
1
) 09 . 9 ( 101 . 2 ) 3 . 265 7 . 275 (
2 1
+ + s s +

94 . 18 86 . 1
2 1
s s

d)
275 . 0
) 09 . 9 ( 2
5
= d
|=0.95 Power = 1 - 0.95 = 0.05

e) | = 0.25
165 . 0
) 09 . 9 ( 2
3
= = d
n*=100 Therefore, n = 51
Brand 1
Brand 2
294 284 274 264 254 244
99
95
90
80
70
60
50
40
30
20
10
5
1
Data
P
e
r
c
e
n
t
Normal Probability Plot for Brand 1...Brand 2
ML Estimates
th
10-15

Section 10-3

10-31 a)
1. The parameters of interest are the mean current (note: set circuit 1 equal to sample 2 so that Table X can be used.
Therefore
1
=mean of circuit 2 and
2
=mean of circuit 1)
2 1 1
2 1 0
: . 3
: . 2

>
=
H
H

4. The test statistic is
1
2 1 2 1
2
2
) 1 )( (
w
n n n n
w
+ + +
=

5. We reject H
0
if w
2
s
*
025 . 0
w = 51, because o=0.025 and n
1
=8 and n
2
=9, Appendix A, Table X gives the critical
value.
6. w
1
= 78and w
2
= 75 and because 75 is less than 51 fail to reject H
0

7. Conclusion, fail to reject H
0
. There is not enough evidence to conclude that the mean of circuit 1 exceeds the mean
of circuit 2.

b)
1. The parameters of interest are the mean image brightness of the two tubes
2 1 1
2 1 0
: . 3
: . 2

>
=
H
H

1
1
1
0
w
w
W
z
o

=

5. We reject H
0
if Z
0
> Z
0.025
= 1.96 for o = 0.025
6. w
1
= 78,
1
w
=72 and
2
1
w
o =108
58 . 0
39 . 10
72 78
0
=
= z

Because Z
0
< 1.96, fail to reject H
0

7. Conclusion: fail to reject H
0
. There is not a significant difference in the heat gain for the heating units at o = 0.05.
P-value = 2[1 - P( Z < 0.58 )] = 0.5619

10-33 a)
1. The parameters of interest are the mean heat gains for heating units
2 1 1
2 1 0
: . 3
: . 2

=
=
H
H

1
2 1 2 1
2
2
) 1 )( (
w
n n n n
w
+ + +
=

6. We reject H
0
if w s
*
01 . 0
w = 78, because o = 0.01 and n
1
= 10 and n
2
= 10, Appendix A, Table X gives the critical
value.
7. w
1
= 77 and w
2
= 133 and because 77 is less than 78, we can reject H
0

8. Conclusion: reject H
0
and conclude that there is a significant difference in the heating units at o = 0.05.

b)
1. The parameters of interest are the mean heat gain for heating units
2 1 1
2 1 0
: . 3
: . 2

=
=
H
H

1
1
1
0
w
w
W
z
o

=

5. Reject H
0
if |Z
0
| > Z
0.025
= 1.96 for o = 0.05
6. w
1
= 77,
1
w
=105 and
2
1
w
o =175
12 . 2
23 . 13
105 77
0
=
= z

th
10-16
Because |Z
0
| > 1.96, reject H
0

0
and conclude that there is a difference in the heat gain for the heating units at o = 0.05.
P-value =2[1 - P( Z < 2.19 )] = 0.034

10-35 a)
1. The parameters of interest are the mean temperatures
2 1 1
2 1 0
: . 3
: . 2

=
=
H
H

1
2 1 2 1
2
2
) 1 )( (
w
n n n n
w
+ + +
=

5. We reject H
0
if w s
*
05 . 0
w = 185, because o = 0.05 and n
1
= 15 and n
2
= 15, Appendix A, Table X gives the critical
value.
6. w
1
= 258 and w
2
= 207 and because both 258 and 207 are greater than 185, we fail to reject H
0

7. Conclusion: fail to reject H
0
. There is not a significant difference in the mean pipe deflection temperature at o =
0.05.

b)
1. The parameters of interest are the mean etch rates
2 1 1
2 1 0
: . 3
: . 2

=
=
H
H

1
1
1
0
w
w
W
z
o

=

5. We reject H
0
if |Z
0
| > Z
0.025
= 1.96 for o=0.05
6. w
1
= 73,
1
w
=105 and
2
1
w
o =175
42 . 2
23 . 13
105 73
0
=
= z

Because |Z
0
| > 1.96, reject H
0

0
. There is a significant difference between the mean etch rates.
P-value = 0.0155
Section 10-4

10-37 a) d = 0.2738 s
d
= 0.1351, n = 9
95% confidence interval:

|
|
.
|
\
|
+ s s
|
|
.
|
\
|

n
s
t d
n
s
t d
d
n d
d
n 1 , 2 / 1 , 2 / o o

|
|
.
|
\
|
+ s s
|
|
.
|
\
|
9
1351 . 0
306 . 2 2738 . 0
9
1351 . 0
306 . 2 2738 . 0
d

0.1699 s
d
s 0.3776

With 95% confidence, the mean shear strength of Karlsruhe method exceeds the mean shear strength of the Lehigh
method by between 0.1699 and 0.3776. Because zero is not included in this interval, the interval is consistent with
rejecting the null hypothesis that the means are equal.

The 95% confidence interval is directly related to a test of hypothesis with 0.05 level of significance and the conclusions
reached are identical.

b) It is only necessary for the differences to be normally distributed for the paired t-test to be appropriate and reliable.
Therefore, the t-test is appropriate.
th
10-17
P-Value: 0.464
A-Squared: 0.318
N: 9
StDev : 0.135099
Av erage: 0.273889
0. 52 0. 42 0. 32 0. 22 0. 12
. 999
. 99
. 95
. 80
. 50
. 20
. 05
. 01
. 001
P
r
o
b
a
b
i
l
i
t
y
diff

10-39 d = 868.375 s
d
= 1290, n = 8 where d
i
= brand 1 - brand 2

|
|
.
|
\
|
+ s s
|
|
.
|
\
|

n
s
t d
n
s
t d
d
n d
d
n 1 , 2 / 1 , 2 / o o

|
.
|
\
|
+ s s |
.
|
\
|
8
1290
499 . 3 375 . 868
8
1290
499 . 3 375 . 868
d

727.46 s
d
s 2464.21

Because this confidence interval contains zero, there is no significant difference between the two brands of tire at a 1%
significance level.

10-41 a) 1) The parameter of interest is the difference in blood cholesterol level,
d

where d
i
= Before After.
2) H
0
:
d
= 0
3) H
1
:
d
> 0

n s
d
t
d
/
0
=

0
> t
0 05 14 . ,
where t
0 05 14 . ,
= 1.761 for o = 0.05
6) d = 26.867
s
d
= 19.04
n =15

465 . 5
15 / 04 . 19
867 . 26
0
= = t

7) Conclusion: Because 5.465 > 1.761 reject the null hypothesis. The data support the claim that the mean difference in
cholesterol levels is significantly less after diet and an aerobic exercise program at the 0.05 level of significance.

P-value=P(t > 5.565) ~ 0


d
d
n
n
s
t d
o
s
|
|
.
|
\
|
1 ,

d
s
|
|
.
|
\
|
15
04 . 19
761 . 1 867 . 26

th
10-18
18.20s
d

Because the lower bound is positive, with 95% confidence the mean difference in blood cholesterol level is significantly
less after the diet and aerobic exercise program.

10-43 a) 1) The parameter of interest is the difference in mean weight,
d

where d
i
=Weight Before Weight After.
2) H
0
:
d
= 0
3) H
1
:
d
> 0
t
d
s n
d
0
=
/

0
> t
0 05 9 . ,
where t
0 05 9 . ,
= 1.833 for o = 0.05
6) = d 17
=
d
s 6.41
= n 10

387 . 8
10 / 41 . 6
17
0
= = t

7) Conclusion: Because 8.387 > 1.833 reject the null hypothesis and conclude that the mean weight loss is significantly
greater than zero. That is, the data support the claim that this particular diet modification program is effective in
reducing weight at the 0.05 level of significance.

b) 1) The parameter of interest is the difference in mean weight loss,
d

where d
i
= Before After.
2) H
0
:
d
= 10
3) H
1
:
d
> 10

n s
d
t
d
/
0
0
A
=

0
> t
0 05 9 . ,
where t
0 05 9 . ,
= 1.833 for o = 0.05
6) d = 17
s
d
= 6.41
n =10

45 . 3
10 / 41 . 6
10 17
0
=
= t

7) Conclusion: Because 3.45 > 1.833 reject the null hypothesis. There is evidence to support the claim that this particular
diet modification program is effective in producing a mean weight loss of at least 10 lbs at the 0.05 level of significance.

c) Use s
d
as an estimate for o:

( )
53 . 3
10
41 . 6 ) 29 . 1 645 . 1 (
10
2
2
= |
.
|
\
| +
=
|
|
.
|
\
| +
=
d
z z
n
o
| o
, n = 4
Yes, the sample size of 10 is adequate for this test.

10-45 a) The probability plot below show that normality assumption is reasonable.
th
10-19

Diff
P
e
r
c
e
n
t
1.0 0.5 0.0 -0.5 -1.0 -1.5
99
95
90
80
70
60
50
40
30
20
10
5
1
Mean
>0.150
-0.015
StDev 0.5094
N 10
KS 0.149
P-Value
Normal Probabiltiy plot of the difference of IQ
Normal

b)
d = 0.015
s
d
= 0.5093
n =10

9 , 025 . 0
t =2.262


|
|
.
|
\
|
+ s s
|
|
.
|
\
|

n
s
t d
n
s
t d
d
n d
d
n 1 , 2 / 1 , 2 / o o

3493 . 0 379 . 0 s s
d

Because zero is contained in the confidence interval there is not sufficient evidence that the mean IQ depends on birth
order.

c) = 1- 0.9 = 0.1
d = 96 . 1
1
= = =
d
s
d
o
o

Thus 6 n would be enough.

10-47 1) Parameters of interest are the median cholesterol levels for two activities.
0
~
: ) 3
0
~
: ) 2
1
0
>
=
D
D
H
H
or
0
~ ~
: ) 3
0
~ ~
: ) 2
2 1 1
2 1 0
>
=

H
H

4) r
-

5) Because o = 0.05 and n = 15, Appendix A, Table VIII gives the critical value of
*
05 . 0
r = 3. We reject
H
0
in favor of H
1
if r
-
s 3.
6) The test statistic is r
-
= 2.

Observation Before After Difference Sign
1 265 229 36 +
2 240 231 9 +
3 258 227 31 +
4 295 240 55 +
5 251 238 13 +
th
10-20
6 245 241 4 +
7 287 234 53 +
8 314 256 58 +
9 260 247 13 +
10 279 239 40 +
11 283 246 37 +
12 240 218 22 +
13 238 219 19 +
14 225 226 -1 -
15 247 233 14 +

P-value = P(R
+

> r
+
= 14 | p = 0.5) =
00049 . 0 ) 5 . 0 ( ) 5 . 0 (
15
20
15
13
=
|
|
.
|
\
|

=
r r
r
r

7) Conclusion: Because the P-value = 0.00049 is less than o = 0.05, reject the null hypothesis. There is a significant
difference in the median cholesterol levels after diet and exercise at o = 0.05.

Section 10-5

10-49 a) f
0.25,5,10
= 1.59 d) f
0.75,5,10
=
1 1
189
0529
0 25 10 5
f
. , ,
.
. = =
b) f
0.10,24,9
= 2.28 e) f
0.90,24,9
=
525 . 0
91 . 1
1 1
24 , 9 , 10 . 0
= =
f

c) f
0.05,8,15
= 2.64 f) f
0.95,8,15
=

10-51 1) The parameters of interest are the standard deviations o o
1 2
,
2) H
0
:
2
2
2
1
o o =
3) H
1
:
2
2
2
1
o o <

2
2
2
1
0
s
s
f =
5) Reject the null hypothesis if f
0
<
4 , 9 , 05 . 0 . 9 , 4 , 95 . 0 .
/ 1 f f = = 1/6 = 0.1666 for o = 0.05
6) n
1
= 5 n
2
= 10 =
2
1
s 23.2 =
2
2
s 28.8
806 . 0
) 8 . 28 (
) 2 . 23 (
0
= = f
7) Conclusion: Because 0.1666 < 0.806 do not reject the null hypothesis.


1 , 1 , 1
2
2
2
1
2
2
2
1
1 2

|
|
.
|
\
|
s
n n
f
s
s
o
o
o

4 , 9 , 05 . 0
2
2
2
1
)
8 . 28
2 . 23
( f s
o
o
where 00 . 6
4 , 9 , 05 .
= f
83 . 4
2
2
2
1
s
o
o
or
20 . 2
2
1
s
o
o

Because the value one is contained within this interval, there is no significant difference in the variances.

10-53 a)
th
10-21
1) The parameters of interest are the standard deviations, o o
1 2
,
2) H
0
: o o
1
2
2
2
=
3) H
1
: o o
1
2
2
2
=

2
2
2
1
0
s
s
f =
0
<
14 , 14 , 975 . 0 .
f = 0.33 or f
0
>
14 , 14 , 025 . 0
f = 3 for o = 0.05
6) n
1
= 15 n
2
= 15 =
2
1
s 2.3 =
2
2
s 1.9
21 . 1
9 . 1
3 . 2
0
= = f
7) Conclusion: Because 0.333 < 1.21 < 3 fail to reject the null hypothesis. There is not sufficient evidence that there is a
difference in the standard deviation.

1 , 1 , 2 /
2
2
2
1
2
2
2
1
1 , 1 , 2 / 1
2
2
2
1
1 2 1 2

|
|
.
|
\
|
s s
|
|
.
|
\
|
n n n n
f
s
s
f
s
s
o o
o
o

3 ) 21 . 1 ( 333 . 0 ) 21 . 1 (
2
2
2
1
s s
o
o

63 . 3 403 . 0
2
2
2
1
s s
o
o


b) 2
2
1
= =
o
o

n
1
= n
2
= 15
= 0.05
Chart VII (o) we find =0.35 then the power 1- = 0.65

c) = 0.05 and 2 /
1 2
o o = so that 2
2
1
=
o
o
and n 31
10-55 a) 1) The parameters of interest are the time to assemble standard deviations, o o
1 2
,
2) H
0
: o o
1
2
2
2
=
3) H
1
: o o
1
2
2
2
=

2
2
2
1
0
s
s
f =
0
<
1 , 1 , 2 / 1
2 1
n n
f
o
= 0.365 or f
0
>
1 , 1 , 2 /
2 1
n n
f
o
= 2.86 for o = 0.02
6) =
1
n 25 =
2
n 21 =
1
s 0.98 =
2
s 1.02

923 . 0
) 02 . 1 (
) 98 . 0 (
2
2
0
= = f

7) Conclusion: Because 0.365 < 0.923 < 2.86 fail to reject the null hypothesis. There is not sufficient evidence to support
the claim that men and women differ in repeatability for this assembly task at the 0.02 level of significance.

ASSUMPTIONS: Assume that the two populations are independent and normally distributed.

th
10-22

1 , 1 , 2 /
2
2
2
1
2
2
2
1
1 , 1 , 2 / 1
2
2
2
1
1 2 1 2

|
|
.
|
\
|
s s
|
|
.
|
\
|
n n n n
f
s
s
f
s
s
o o
o
o

73 . 2 ) 923 . 0 ( 350 . 0 ) 923 . 0 (
2
2
2
1
s s
o
o

527 . 2 323 . 0
2
2
2
1
s s
o
o

Because the value one is contained within this interval, there is no significant difference between the variance of the
repeatability of men and women for the assembly task at a 2% significance level.

10-57 a) 90% confidence interval for the ratio of variances:

1 , 1 , 2 / 2
2
2
1
2
2
2
1
1 , 1 , 2 / 1 2
2
2
1
1 2 1 2

|
|
.
|
\
|
s s
|
|
.
|
\
|
n n n n
f
s
s
f
s
s
o o
o
o

445 . 2
40 . 0
35 . 0
421 . 0
40 . 0
35 . 0
2
2
2
1
|
.
|
\
|
s s |
.
|
\
|
o
o

139 . 2 369 . 0
2
2
2
1
s s
o
o

463 . 1 607 . 0
2
1
s s
o
o


1 , 1 , 2 / 2
2
2
1
2
2
2
1
1 , 1 , 2 / 1 2
2
2
1
1 2 1 2

|
|
.
|
\
|
s s
|
|
.
|
\
|
n n n n
f
s
s
f
s
s
o o
o
o

82 . 2
40 . 0
35 . 0
342 . 0
40 . 0
35 . 0
2
2
2
1
|
.
|
\
|
s s |
.
|
\
|
o
o

558 . 2 311 . 0
2
2
2
1
s s
o
o

599 . 1 557 . 0
2
1
s s
o
o

The 95% confidence interval is wider than the 90% confidence interval.

c) 90% lower-sided confidence interval:

2
2
2
1
1 , 1 , 1 2
2
2
1
1 2
o
o
o
s
|
|
.
|
\
|
n n
f
s
s

2
2
2
1
512 . 0
40 . 0
35 . 0
o
o
s |
.
|
\
|

2
2
2
1
448 . 0
o
o
s

2
1
669 . 0
o
o
s

10-59 1) The parameters of interest are the melting variances, o o
1
2
2
2
,
2) H
0
: o o
1
2
2
2
=
3) H
1
: o o
1
2
2
2
=

2
2
2
1
0
s
s
f =
0
< f
0 975 20 20 . , ,
where f
0 975 20 20 . , ,
= 0.4058 or f
0
> f
0 025 20 20 . , ,
where
f
0 025 20 20 . , ,
= 2.46 for o = 0.05
6) n
1
= 21 n
2
= 21
s
1
= 4 s
2
= 3

78 . 1
) 3 (
) 4 (
2
2
0
= = f

7) Conclusion: Because 0.4058 < 1.78 < 2.46 fail to reject the null hypothesis. The population variances do not differ at
the 0.05 level of significance.

10-61 1) The parameters of interest are the overall distance standard deviations, o o
1 2
,
th
10-23
2) H
0
: o o
1
2
2
2
=
3) H
1
: o o
1
2
2
2
=
f
s
s
0
1
2
2
2
=
0
<
9 , 9 , 975 . 0 .
f =0.248 or f
0
>
9 , 9 , 025 . 0
f = 4.03 for o = 0.05
6) n
1
= 10 n
2
= 10 =
1
s 8.03 s
2
= 10.04

640 . 0
) 04 . 10 (
) 03 . 8 (
2
2
0
= = f

7) Conclusion: Because 0.248 < 0.640 < 4.04 fail to reject the null hypothesis. There is not sufficient evidence that the
standard deviations of the overall distances of the two brands differ at the 0.05 level of significance.


1 , 1 , 2 /
2
2
2
1
2
2
2
1
1 , 1 , 2 / 1
2
2
2
1
1 2 1 2

|
|
.
|
\
|
s s
|
|
.
|
\
|
n n n n
f
s
s
f
s
s
o o
o
o

03 . 4 ) 640 . 0 ( 248 . 0 ) 640 . 0 (
2
2
2
1
s s
o
o

579 . 2 159 . 0
2
2
2
1
s s
o
o

A 95% lower confidence bound on the ratio of standard deviations is given by
1
2
0.399 1.606
o
o
s s

Because the value one is contained within this interval, there is no significant difference in the variances of the distances
at a 5% significance level.

10-63 1) The parameters of interest are the variances of the weight measurements between the two sheets of paper,
2
2
2
1
,o o
2) H
0
: o o
1
2
2
2
=
3) H
1
: o o
1
2
2
2
=

2
2
2
1
0
s
s
f =
0
<
14 , 14 , 975 . 0 .
f = 0.33 or f
0
>
14 , 14 , 025 . 0
f = 3 for o = 0.05
6) n
1
= 15 n
2
= 15 =
2
1
s 0.00831
2
=
2
2
s 0.00714
2

35 . 1
0
= f
7) Conclusion: Because 0.333 < 1.35 < 3 fail to reject the null hypothesis. There is not sufficient evidence that there is a
difference in the variances of the weight measurements between the two sheets of paper.

1 , 1 , 2 /
2
2
2
1
2
2
2
1
1 , 1 , 2 / 1
2
2
2
1
1 2 1 2

|
|
.
|
\
|
s s
|
|
.
|
\
|
n n n n
f
s
s
f
s
s
o o
o
o

3 ) 35 . 1 ( 333 . 0 ) 35 . 1 (
2
2
2
1
s s
o
o

05 . 4 45 . 0
2
2
2
1
s s
o
o


10-65 a) 1) The parameters of interest are the etch-rate variances, o o
1
2
2
2
, .
2) H
0
: o o
1
2
2
2
=
th
10-24
3) H
1
: o o
1
2
2
2
=

2
2
2
1
0
s
s
f =
0
< f
0 975 9 9 . , ,
= 0.248 or f
0
> f
0 025 9 9 . , ,
= 4.03 for o = 0.05
6) n
1
= 10 n
2
= 10
s
1
= 0.422 s
2
= 0.231
337 . 3
) 231 . 0 (
) 422 . 0 (
2
2
0
= = f
7) Conclusion: Because 0.248 < 3.337 < 4.03 fail to reject the null hypothesis. There is not sufficient evidence that the
etch rate variances differ at the 0.05 level of significance.

b) With 10 . 0 4 . 1 2 = = = | and o = 0.05, we find from Chart VII (o) that n
1
*
= n
2
*
= 100. Therefore, the samples of
size 10 would not be adequate.

Section 10-6

10-67 a) This is one-sided test because the hypotheses are p
1
p
2
= 0 versus greater than 0.
b)
752 . 0
250
188
1
= = p

7 . 0
350
245
2
= = p

7217 . 0
350 250
245 188
=
+
+
= p

Test statistic is
|
|
.
|
\
|
+
=
2 1
2 1
0
1 1
) 1 (

n n
p p
p p
z
where
2 1
2 1
n n
x x
p
+
+
=

4012 . 1
350
1
250
1
) 7217 . 0 1 )( 7217 . 0 (
052 . 0
0
=
|
.
|
\
|
+
= z

P-value = [1- P(Z < 1.4012)] = 1 - 0.9194 = 0.0806

95% lower confidence interval on the difference:

2 1
2
2 2
1
1 1
2 1
) 1 ( ) 1 (
) ( p p
n
p p
n
p p
z p p s

o

2 1
350
) 7 . 0 1 ( 7 . 0
250
) 752 . 0 1 ( 752 . 0
65 . 1 ) 052 . 0 ( p p s

2 1
0085 . 0 p p s

c) The P-value = 0.0806 is less than o = 0.10. Therefore, we reject the null hypothesis that p
1
p
2
= 0 at the 0.1 level of
significance. If o = 0.05, the P-value = 0.0806 is greater than o = 0.05 and we fail to reject the null hypothesis.

10-69 a) 1) The parameters of interest are the proportion of voters in favor of Bush vs those in favor of Kerry, p
1
and
p
2

2) H
0
: p p
1 2
=
3) H
1
: p p
1 2
=
4) Test statistic is
|
|
.
|
\
|
+
=
2 1
2 1
0
1 1
) 1 (

n n
p p
p p
z
where
2 1
2 1
n n
x x
p
+
+
=

5) Reject the null hypothesis if z
0
< z
0 025 .
or z
0
> z
0 025 .
where z
0 025 .
= 1.96 for o = 0.05
th
10-25
6) n
1
= 2020 n
2
= 2020
x
1
= 1071 x
2
= 930
p
1
= 0.53 p
2
= 0.46
495 . 0
2020 2020
930 1071
=
+
+
= p

45 . 4
2020
1
2020
1
) 495 . 0 1 ( 495 . 0
46 . 0 53 . 0
0
=
|
.
|
\
|
+
= z

7) Conclusion: Because 4.45 > 1.96 reject the null hypothesis and conclude yes there is a significant difference in the
proportions at the 0.05 level of significance.

P-value = 2[1 P(Z < 4.45)] 0

b) 95% confidence interval on the difference:

( )
( ) ( )
( )
( ) ( )
/ /
p p z
p p
n
p p
n
p p p p z
p p
n
p p
n
1 2 2
1 1
1
2 2
2
1 2 1 2 2
1 1
1
2 2
2
1 1 1 1

+

s s +

+

o o

1 . 0 039 . 0
2 1
s s p p

Because this interval does not contain the value zero, we are 95% confident there is a difference in the proportions.

10-71 a) 1) The parameters of interest are the proportion of satisfactory lenses, p
1
and p
2

2) H
0
:
2 1
p p =
3) H
1
:
2 1
p p =
4) Test statistic is

|
|
.
|
\
|
+
=
2 1
2 1
0
1 1
) 1 (

n n
p p
p p
z
where
2 1
2 1
n n
x x
p
+
+
=

5) Reject the null hypothesis if z
0
<
005 . 0
z or z
0
>
005 . 0
z where
005 . 0
z = 2.58 for o = 0.01
6) n
1
= 300 n
2
= 300
x
1
= 253 x
2
= 196
=
1
p 0.843 =
2
p 0.653
748 . 0
300 300
196 253
=
+
+
= p

36 . 5
300
1
300
1
) 748 . 0 1 ( 748 . 0
653 . 0 843 . 0
0
=
|
.
|
\
|
+
= z

7) Conclusion: Because 5.36 > 2.58 reject the null hypothesis and conclude yes there is a significant difference in the
fraction of polishing-induced defects produced by the two polishing solutions at the 0.01 level of significance.

P-value = 2[1 P(Z < 5.36)] 0

b) By constructing a 99% confidence interval on the difference in proportions, the same question can be answered by
whether or not zero is contained in the interval.

Supplemental Exercises

10-73 a) SE Mean
1

50 . 0
20
23 . 2
1
1
= = =
n
s

=
1
x 11.87 x
2
= 12.73 s
1
2
= 2.23
2
s
2
2
= 3.19
2
n
1
= 20 n
2
= 20
Degrees of freedom = n
1
+ n
2
- 2 = 20 20 - 2 = 38.

th
10-26
7522 . 2
2 20 20
19 . 3 ) 1 20 ( 23 . 2 ) 1 20 (
2
) 1 ( ) 1 (
2 2
2 1
2
2 2
2
1 1
=
+
+
=
+
+
=
n n
s n s n
s
p

9881 . 0
20
1
20
1
7522 . 2
) 86 . 0 (
1 1
) (
2 1
0 2 1
0
=
+
=
+
A
=
n n
s
x x
t
p

P-value = 2 [P(t < 0.9881)] and 2(0.10) <P-value < 2(0.25) = 0.20 <P-value < 0.5

The 95% two-sided confidence interval:
024 . 2
38 , 025 . 0 2 , 2 /
2 1
= =
+
t t
n n o

( ) ( )
2 1
2 1 2 1
2 1
2 , 2 / 2 1
1 1 1 1
2
2 1
, 2 / 2 1
n n
s t x x
n n
s t x x
p p n n
n n
+ + s s +
+
+
o

o

( ) ( )
20
1
20
1
) 7522 . 2 )( 024 . 2 ( 86 . 0
20
1
20
1
) 7522 . 2 )( 024 . 2 ( 86 . 0
2 1
+ + s s +

902 . 0 622 . 2
2 1
s s

b) This is two-sided test because the alternative hypothesis is
1

2
not = 0.

c) Because the 0.20 < P-value < 0.5 and the P-value > o = 0.05 we fail to reject the null hypothesis at the 0.05 level of
significance. If o = 0.01, we also fail to reject the null hypothesis.

10-75 a) Assumptions that must be met are normality, equality of variance, and independence of the observations. Normality
and equality of variances appear to be reasonable from the normal probability plots. The data appear to fall along straight
lines and the slopes appear to be the same. Independence of the observations for each sample is obtained if random
samples are selected.
.
P-Value: 0.899
A-Squared: 0.171
N: 9
StDev : 2.06949
Av erage: 16.3556
20 19 18 17 16 15 14
. 999
. 99
. 95
. 80
. 50
. 20
. 05
. 01
. 001
P
r
o
b
a
b
i
l
i
t y
9-hour
P-Value: 0.903
A-Squared: 0.158
N: 6
StDev : 2.37016
Av erage: 11.4833
15 14 13 12 11 10 9 8
. 999
. 99
. 95
. 80
. 50
. 20
. 05
. 01
. 001
P
r
o
b
a
b
i
l
i
t y
1-hour

b) x
1
1636 = . 483 . 11
2
= x
s
1
2 07 = . s
2
2 37 = .
n
1
9 = n
2
6 =
99% confidence interval: t t
n n o/ , . , 2 2 0 00513
1 2
+
= where t
0 005 13 . ,
= 3.012

19 . 2
13
) 37 . 2 ( 5 ) 07 . 2 ( 8
2 2
=
+
=
p
s

( ) ( ) ( ) ( )
2 1
2 , 2 / 2 1 2 1
2 1
2 , 2 / 2 1
1 1 1 1
2 1 2 1
n n
s t x x
n n
s t x x
p n n p n n
+ + s s +
+ + o o

( ) ( ) ( ) ( )
6
1
9
1
19 . 2 012 . 3 483 . 11 36 . 16
6
1
9
1
19 . 2 012 . 3 483 . 11 36 . 16
2 1
+ + s s +

36 . 8 40 . 1
2 1
s s

c) Yes, we are 99% confident the results from the first test condition exceed the results of the second test
condition because the confidence interval contains only positive values.

d) 95% confidence interval for o o
1
2
2
2
/
th
10-27

2075 . 0
82 . 4
1 1
8 , 5 , 025 . 0
5 , 8 , 975 . 0
= = =
f
f
, 76 . 6
5 , 8 , 025 . 0
= f

673 . 3 113 . 0
) 817 . 4 (
617 . 5
283 . 4
) 148 . 0 (
617 . 5
283 . 4
2
2
2
1
2
2
2
1
8 , 5 , 025 . 0
2
2
2
1
2
2
2
1
8 , 5 , 975 . 0
2
2
2
1
s s
|
.
|
\
|
s s |
.
|
\
|
s s
o
o
o
o
o
o
f
s
s
f
s
s

e) Because the value one is contained within this interval, the population variances do not differ at a 5% significance
level.

10-77 a) 1) The parameter of interest is the mean weight loss,
d

where d
i
= Initial Weight Final Weight.
2) H
0
:
d
= 3
3) H
1
:
d
> 3
t
d
s n
d
0
0
=
A
/

5) Reject H
0
if t
0
> t
o,n-1
where t
0.05,7
= 1.895for o = 0.05.
6) d = 4125 .

s
n
d
=
=
1246
8
.

t
0
4125 3
1246 8
2554 =

=
.
. /
.
7) Conclusion: Because 2.554 > 1.895, reject the null hypothesis and conclude the mean weight loss is greater than
3 at o = 0.05.

b) 2) H
0
:
d
= 3
3) H
1
:
d
> 3
t
d
s n
d
0
0
=
A
/

5) Reject H
0
if t
0
> t
o,n-1
where t
0.01,7
= 2.998 for o = 0.01.
6) d = 4125 .

s
n
d
=
=
1246
8
.

t
0
4125 3
1246 8
2554 =

=
.
. /
.
7) Conclusion: Because 2.554 < 2.998, fail to reject the null hypothesis. There is not sufficient evidence to conclude
that the mean weight loss is greater than 3 at o = 0.01.

c) 2) H
0
:
d
= 5
3) H
1
:
d
> 5
t
d
s n
d
0
0
=
A
/

5) Reject H
0
if t
0
> t
o,n-1
where t
0.05,7
=1.895 for o = 0.05
6) d = 4125 .
th
10-28

s
n
d
=
=
1246
8
.

t
0
4125 5
1246 8
1986 =

=
.
. /
.
7) Conclusion: Because 1.986 < 1.895, fail to reject the null hypothesis. There is not sufficient evidence to conclude
that the mean weight loss is greater than 5 at o = 0.05.

d)
2) H
0
:
d
= 5
3) H
1
:
d
> 5
t
d
s n
d
0
0
=
A
/

5) Reject H
0
if t
0
> t
o,n-1
where t
0.01,7
= 2.998 for o = 0.01.
6) d = 4125 .

s
n
d
=
=
1246
8
.

t
0
4125 5
1246 8
1986 =

=
.
. /
.
7) Conclusion: Because 1.986 < 2.998, fail to reject the null hypothesis. There is not sufficient evidence to
conclude that the mean weight loss is greater than 5 at o = 0.01.

10-79 a) 1) The parameters of interest are the proportions of children who contract polio, p
1
, p
2

2) H
0
: p
1
= p
2

3) H
1
: p
1
= p
2


|
|
.
|
\
|
+
=
2 1
2 1
0
1 1
) 1 (

n n
p p
p p
z

5) Reject H
0
if z
0
< z
o/2
or z
0
> z
o/2
where z
o/2
= 1.96 for o = 0.05
6) . p
x
n
1
1
1
110
201299
000055 = = = (Placebo) . p
x x
n n
=
+
+
=
1 2
1 2
0000356
. p
x
n
2
2
2
33
200745
000016 = = = (Vaccine)
z
0
000055 000016
0000356 1 0000356
1
201299
1
200745
655 =

+
|
\
|
.
|
=
. .
. ( . )
.
7) Because 6.55 > 1.96 reject H
0
and conclude the proportion of children who contracted polio is significantly
different at o = 0.05.

b) o = 0.01
Reject H
0
if z
0
< z
o/2
or z
0
> z
o/2
where z
o/2
=2.58. Still z
0
= 6.55.
Because 6.55 > 2.58, reject H
0
and conclude the proportion of children who contracted polio is significantly different at
o = 0.01.

c) The conclusions are the same because z
0
is large enough to exceed z
o/2
in both cases.

10-81 . p
x
n
1
1
1
387
1500
0258 = = = . p
x
n
2
2
2
310
1200
02583 = = =
th
10-29

a) z z
o/ .
.
2 0 025
196 = =
( ) 0258 02583 196
0258 0742
1500
02583 07417
1200
. . .
. ( . ) . ( . )
+

0329 . 0 0335 . 0
2 1
s s p p

Because zero is contained in this interval, there is no significant difference between the proportions of unlisted numbers
in the two cities at a 5% significance level.

b) z z
o/ .
.
2 0 05
165 = =

( ) 0258 02583 165
0258 0742
1500
02583 07417
1200
. . .
. ( . ) . ( . )
+
s s 00282 00276
1 2
. . p p
The proportions of unlisted numbers in the two cities do not significantly differ at a 5% significance level.

c) . p
x
n
1
1
1
774
3000
0258 = = =
. p
x
n
2
2
2
620
2400
02583 = = =
( ) 0258 02583 196
0258 0742
3000
02583 07417
2400
. . .
. ( . ) . ( . )
+ s s 00238 00232
1 2
. . p p
( ) 0258 02583 165
0258 0742
3000
02583 07417
2400
. . .
. ( . ) . ( . )
+
0195 . 0 0201 . 0
2 1
s s p p

Increasing the sample size decreased the width of the confidence intervals, but did not change the conclusions drawn.
The conclusion remains that there is no significant difference.

10-83 a) Yes, there could be some bias in the results due to the telephone survey.
b) If it could be shown that these populations are similar to the respondents, the results may be extended.

10-85 =
1
x 30.87 x
2
= 30.68
=
1
o 0.10 o
2
= 0.15
n
1
= 12 n
2
= 10

a) 90% two-sided confidence interval:
( ) ( )
2
2
2
1
2
1
2 / 2 1 2 1
2
2
2
1
2
1
2 / 2 1
n n
z x x
n n
z x x
o o

o o
o o
+ + s s +

( )
10
) 15 . 0 (
12
) 10 . 0 (
645 . 1 68 . 30 87 . 30
10
) 15 . 0 (
12
) 10 . 0 (
645 . 1 ) 68 . 30 87 . 30 (
2 2
2 1
2 2
+ + s s +

2813 . 0 0987 . 0
2 1
s s
We are 90% confident that the mean fill volume for machine 1 exceeds that of machine 2 by between 0.0987 and
0.2813 fl. oz.

b) 95% two-sided confidence interval:
( ) ( ) x x z
n n
x x z
n n
1 2 2
1
2
1
2
2
2
1 2 1 2 2
1
2
1
2
2
2
+ s s + +
o o
o o

o o
/ /

( ) ( . . ) .
( . ) ( . )
. . .
( . ) ( . )
3087 3068 196
010
12
015
10
3087 3068 196
010
12
015
10
2 2
1 2
2 2
+ s s + +
th
10-30
299 . 0 0812 . 0
2 1
s s

We are 95% confident that the mean fill volume for machine 1 exceeds that of machine 2 by between 0.0812 and 0.299
fl. oz.

Comparison of parts (a) and (b): As the level of confidence increases, the interval width also increases (with all other
values held constant).

c) 95% upper-sided confidence interval:
( )
o o
o 1 2 1 2
1
2
1
2
2
2
s + + x x z
n n

( )
1 2
2 2
3087 3068 1645
010
12
015
10
s + + . . .
( . ) ( . )

1 2
02813 s .

With 95% confidence, the fill volume for machine 1 exceeds the fill volume of machine 2 by no more than 0.2813 fl.
oz.

d) 1) The parameter of interest is the difference in mean fill volume
1 2

2) H
0
:
1 2
0 = or
1 2
=
3) H
1
:
1 2
0 = or
1 2
=
z
x x
n n
0
1 2 0
1
2
1
2
2
2
=

+
( ) A
o o

5) Reject H
0
if z
0
< z
o/2
= 1.96 or z
0
> z
o/2
= 1.96 for o = 0.05
6) x
1
= 30.87 x
2
= 30.68
o
1
= 0.10 o
2
= 0.15
n
1
= 12 n
2
= 10

42 . 3
10
) 15 . 0 (
12
) 10 . 0 (
) 68 . 30 87 . 30 (
2 2
0
=
+
= z

7) Because 3.42 > 1.96 reject the null hypothesis and conclude the mean fill volumes of machine 1 and
machine 2 differ at o = 0.05.

P-value = 00062 . 0 ) 99969 . 0 1 ( 2 )] 42 . 3 ( 1 [ 2 = = u

e) Assume the sample sizes are to be equal, use o = 0.05, | = 0.10, and A = 0.20

( ) ( )
( )
( )
( )
n
z z
~
+ +
=
+ +
=
o |
o o
/
. . ( . ) ( . )
( . )
. ,
2
2
1
2
2
2
0
2
2
2 2
2
196 128 010 015
020
853
A A
n = 9, use n
1
= n
2
= 9
10-87 a) 1) The parameters of interest are: the proportion of lenses that are unsatisfactory after tumble-polishing, p
1,
p
2

2) H
0
: p
1
= p
2

3) H
1
: p
1
= p
2

z
p p
p p
n n
0
1 2
1 2
1
1 1
=

+
|
\
|
.
|

( )

5) Reject H
0
if z
0
< z
o/2
or z
0
> z
o/2
where z
o/2
= 2.58 for o = 0.01.
6) x
1
=number of defective lenses
th
10-31
. p
x
n
1
1
1
47
300
01567 = = = . p
x x
n n
=
+
+
=
1 2
1 2
02517
.. p
x
n
2
2
2
104
300
0 3467 = = =
z
0
01567 03467
02517 1 02517
1
300
1
300
536 =

+
|
\
|
.
|
=
. .
. ( . )
.
7) Conclusion: Because 5.36 < 2.58 reject H
0
and conclude that the proportions from the two polishing fluids are
different.

b) The conclusions are the same whether we analyze the data using the proportion unsatisfactory or
proportion satisfactory.

c)

60
4 . 59
09 . 0
346 . 5
) 6 . 0 9 . 0 (
) 4 . 0 ( 6 . 0 ) 1 . 0 ( 9 . 0 28 . 1
2
) 4 . 0 1 . 0 )( 6 . 0 9 . 0 (
575 . 2
2
2
=
= =
|
|
.
|
\
|
+ +
+ +
=
n
n

10-89 a) No
P-Value: 0.011
A-Squared: 0.934
N: 10
StDev : 0.302030
Av erage: 24.67
24. 9 24. 4 23. 9
. 999
. 99
. 95
. 80
. 50
. 20
. 05
. 01
. 001
P
r
o
b
a
b
i
l
i
t y
mercedes
P-Value: 0.000
A-Squared: 1.582
N: 10
StDev : 3.89280
Av erage: 40.25
40 35 30
. 999
. 99
. 95
. 80
. 50
. 20
. 05
. 01
. 001
P
r
o
b
a
b
i
l
i
t y
volkswag

b) The normal probability plots indicate that the data follow normal distributions because the data appear to fall along
straight lines. The plots also indicate that the variances appear to be equal because the slopes appear to be the same.
P-Value: 0.329
A-Squared: 0.381
N: 10
StDev : 0.142984
Av erage: 24.74
24. 9 24. 8 24. 7 24. 6 24. 5
. 999
. 99
. 95
. 80
. 50
. 20
. 05
. 01
. 001
P
r
o
b
a
b
i
l
i
t y
mercedes
P-Value: 0.230
A-Squared: 0.440
N: 10
StDev : 1.21952
Av erage: 41.25
42. 5 41. 5 40. 5 39. 5
. 999
. 99
. 95
. 80
. 50
. 20
. 05
. 01
. 001
P
r
o
b
a
b
i
l
i
t y
volkswag

th
10-32
c) By correcting the data points, it is more apparent the data follow normal distributions. Note that one unusual
observation can cause an analyst to reject the normality assumption.
d) Consider a one-sided 95% confidence interval on the ratio of the variances, o o
V M
2 2
/

314 . 0
18 . 3
1 1
0204 . 0
49 . 1
05 . 0 , 9 , 9
95 . 0 , 9 , 9
2
2
= = = =
=
f
f s
s
M
V

2
2
2
2
2
2
95 . 0 , 9 , 9 2
2
93 . 22
314 . 0
0204 . 0
49 . 1
M
V
M
V
M
V
M
V
f
s
s
o
o
o
o
o
o
<
< |
.
|
\
|
<
|
|
.
|
\
|

Because the interval does not include the value one, we reject the hypothesis that variability in mileage performance is the
same for the two types of vehicles. There is evidence that the variability is greater for a Volkswagen than for a Mercedes.

e) 1) The parameters of interest are the variances in mileage performance,
2 2
,
M V
o o
2) H
0
:
2 2
M V
o o =
3) H
1
:
2 2
M V
o o >

2
2
0
M
V
s
s
f =
5) Reject H
0
if f
0
>
9 , 9 , 05 . 0
f where
9 , 9 , 05 . 0
f = 3.18 for o = 0.05

6) s
1
= 1.22 s
2
= 0.143
n
1
= 10 n
2
= 10
f
0
2
2
122
0143
7278 = =
( . )
( . )
.
7) Conclusion: Because 72.78 > 3.28 reject H
0
and conclude that there is a significant difference between Volkswagen
and Mercedes in terms of mileage variability. The same conclusions are reached in part (d).
Recall
95 . 0 , 9 , 9
05 . 0 , 9 , 9
1
f
f = . The hypothesis test rejects when
9 , 9 , 05 . 0 2
2
0
f
s
s
f
M
V
> = and this is equivalent to
9 , 9 , 95 . 0
2
2
1
f s
s
M
V
> and this is also equivalent to the lower confidence limit 1
9 , 9 , 95 . 0 2
2
> f
s
s
M
V
. Consequently the tests
rejects when the lower confidence limit exceeds one.

10-91

a) The assumption of normality appears to be reasonable. The data lie along a straight line in the normal probability
plot.
th
10-33
P-Value: 0.128
A-Squared: 0.526
N: 9
StDev : 1.30171
Av erage: -0.222222
2 1 0 -1 -2
. 999
. 99
. 95
. 80
. 50
. 20
. 05
. 01
. 001
P
r
o
b
a
b
i
l
i
t
y
diff

b) 1) The parameter of interest is the mean difference in tip hardness,
d

2) H
0
:
d
= 0
3) H
1
:
d
= 0
t
d
s n
d
0
=
/

5) Since no significance level is given, we calculate the P-value. Reject H
0
if the P-value is sufficiently small.
6) d = 0222 .

s
n
d
=
=
130
9
.

t
0
0222
130 9
0512 =

=
.
. /
.
P-value = 2P(T < -0.512) = 2P(T > 0.512) and 2(0.25) < P-value < 2(0.40). Thus, 0.50 < P-value < 0.80

7) Conclusion: Because the P-value is larger than common levels of significance, fail to reject H
0
and conclude there is
no significant difference in mean tip hardness.

c) | = 0.10

o
d
d
d
=
= = =
1
1 1
13
0769
.
.

From Chart VII (f) with o = 0.01, n = 30

10-93 a) The data from both depths appear to be normally distributed, but the slopes do not appear to be equal.
Therefore, it is not reasonable to assume that
2
2
2
1
o o =
.
surface
bottom
4 5 6 7 8
1
5
10
20
30
40
50
60
70
80
90
95
99
Data
P
e
r
c
e
n
t
Normal Probability Plot for surface...bottom
ML Estimates
th
10-34
b) 1) The parameter of interest is the difference in mean HCB concentration,
1 2
, with A
0
= 0
2) H
0
:
1 2
0 = or
1 2
=
3) H
1
:
1 2
0 = or
1 2
=
t
x x
s
n
s
n
0
1 2 0
1
2
1
2
2
2
=

+
( ) A

0
<
15 , 025 . 0
t or t
0
>
15 , 025 . 0
t where
15 , 025 . 0
t = 2.131 for o = 0.05. Also

15
06 . 15
1 1
2
2
2
2
1
2
1
2
1
2
2
2
2
1
2
1
~
=
|
|
.
|
\
|
+
|
|
.
|
\
|
|
|
.
|
\
|
+
=
v
v
n
n
s
n
n
s
n
s
n
s

(truncated)

6) x
1
= 4.804 x
2
= 5.839 s
1
= 0.631 s
2
= 1.014
n
1
= 10 n
2
= 10

74 . 2
10
) 014 . 1 (
10
) 631 . 0 (
) 839 . 5 804 . 4 (
2 2
0
=
+
= t

7) Conclusion: Because 2.74 < 2.131 reject the null hypothesis. Conclude that the mean HCB concentration is
different at the two depths sampled at the 0.05 level of significance.

c) Assume the variances are equal. Then A = 2, o = 0.05, n = n
1
= n
2
= 10, n* = 2n 1 = 19, s
p
= 0.84

and
2 . 1
) 84 . 0 ( 2
2
= = d
. From Chart VII (e) we find | 0.05, and then calculate power = 1 | = 0.95

d) Assume the variances are equal. Then A = 1, o = 0.05, n = n
1
= n
2
, n* = 2n 1, | = 0.1, s
p
= 0.84 1

and
6 . 0
) 84 . 0 ( 2
1
= = d
. From Chart VII (e) we find n* = 50 and
5 . 25
2
1 50
=
+
= n
, so n = 26.

Mind-Expanding Exercises
10-95 The
2
2
2
1
2
1
2 1
) (
n n
X X V
o o
+ =
and suppose this is to equal a constant k. Then, we are to minimize
2 2 1 1
n C n C +
subject to k
n n
= +
2
2
2
1
2
1
o o
. Using a Lagrange multiplier, we minimize by setting the partial derivatives of
|
|
.
|
\
|
+ + + = k
n n
n C n C n n f
2
2
2
1
2
1
2 2 1 1 2 1
) , , (
o o

with respect to n
1
, n
2
and equal to zero.
These equations are

0 ) , , (
2
1
2
1
1 2 1
1
= =
n
C n n f
n
o
c
c
(1)

0 ) , , (
2
2
2
2
2 2 1
2
= =
n
C n n f
n
o
c
c
(2)
th
10-35

k
n n
n n f = + =
2
2
2
1
2
1
2 1
) , , (
o o
c
c
(3)
Upon adding equations (1) and (2), we obtain
0
2
2
2
1
2
1
2 1
=
|
|
.
|
\
|
+ +
n n
C C
o o

Substituting from equation (3) enables us to solve for to obtain
=
+
k
C C
2 1
Then, equations (1) and (2) are solved for n
1
and n
2
to obtain
2
2 1
2
2
2
1
2 1
2
1
1
) ( ) (
kC
C C
n
kC
C C
n
+
=
+
=
o o

It can be verified that this is a minimum and that with these choices for n
1
and n
2
.

2
2
2
1
2
1
2 1
) (
n n
X X V
o o
+ =
.

10-97 a) ) (
c o c
o

< > = z Z or z Z P where Z has a standard normal distribution.
Then, o c o c o
c o c
= + = < + > =

) ( ) ( z Z P z Z P
b) | o
o c c
= < < = +
P z Z z ( | )
0 1 0

10-99 a)
2
1
p
p
= u and
2
1
p
p
= u and
] / ) ( / ) ( ), [ln( ~ )
ln(
2 2 2 2 1 1 1 1
x n x n x n x n N + u u

The (1 o) confidence interval for ln(u) can use the relationship
4 / 1
2 2
2 2
1 1
1 1
) ln( )
ln(
|
|
.
|
\
|
|
|
.
|
\
|
+
|
|
.
|
\
|

=
x n
x n
x n
x n
Z
u u

4 / 1
2 2
2 2
1 1
1 1
2
4 / 1
2 2
2 2
1 1
1 1
2
)
ln( ) ln( )
ln(
|
|
.
|
\
|
|
|
.
|
\
|
+
|
|
.
|
\
|
+ s s
|
|
.
|
\
|
|
|
.
|
\
|
+
|
|
.
|
\
|
x n
x n
x n
x n
Z
x n
x n
x n
x n
Z
o o
u u u

b) The (1 o) confidence interval for u can use the CI developed in part (a) where u = e^( ln(u))

1/ 4 1/ 4
1 1 2 2 1 1 2 2
2 2
1 1 2 2 1 1 2 2

n x n x n x n x
Z Z
n x n x n x n x
e e
o o
u u u
| | | | | | | | | | | |
+ +
| | | | | |
| |
\ . \ . \ . \ . \ . \ .
s s

c)

1 1 2 2 1 1 2 2
2 2
1 1 2 2 1 1 2 2
1 / 4
.25 .25
100 27 100 19 100 27 100 19
1.96 1.96
2700 1900 2700 1900

1.42 1.42
n x n x n x n x
Z Z
n x n x n x n x
e e
e e
o o
u u u
u
| | | | | | | | | | | |
+ + | | | | | |
| |
\ . \ . \ . \ . \ . \ .
| | | | | | | | | | |
+ +
| | | | |
\ . \ . \ . \ . \ . \
s s
s s
1 / 4
0.519 3.887 u
|
|
.
s s

th
10-36
Because the confidence interval contains the value one, we conclude that there is no significant difference in the
proportions at the 95% level of significance.

CH 10

Caricato da

Informazioni sul documento

Titolo originale

Copyright

Formati disponibili

Condividi questo documento

Condividi o incorpora il documento

Opzioni di condivisione

Hai trovato utile questo documento?

Questo contenuto è inappropriato?

Copyright:

Formati disponibili

CH 10

Caricato da

Copyright:

Formati disponibili

Applied Statistics and Probability for Engineers, 5

Potrebbero piacerti anche