ch04 PDF

Chapter 4
Inferences About Process Quality
LEARNING OBJECTIVES
After completing this chapter you should be able to:
1. Explain the concept of random sampling
2. Explain the concept of a sampling distribution
3. Explain the general concept of estimating the parameters of a population or probability
distribution
4. Know how to explain the precision with which a parameter is estimated
5. Construct and interpret confidence intervals on a single mean and on the difference in two
means
6. Construct and interpret confidence intervals on a single variance or the ratio of two variances
7. Construct and interpret confidence intervals on a single proportion and on the difference in two
proportions
8. Test hypotheses on a single mean and on the differences in two means
9. Test hypotheses on a single variance and on the ratio of two variances
10. Test hypotheses on a single proportion and on the difference in two proportions
11. Use the P-value approach for hypothesis testing
12. Understand how the analysis of variance (ANOVA) is used to test hypotheses about the equality
of more than two means
13. Understand how to fit and interpret linear regression models
IMPORTANT TERMS AND CONCEPTS

Alternative hypothesis Point estimator
Analysis of variance (ANOVA) Poisson distribution
Binomial distribution Pooled estimator
Checking assumptions for statistical inference Power of a statistical test
procedures
Chi-square distribution Random sample
Confidence interval Regression model
Confidence intervals on means, known variance(s) Residual analysis
4-2 CHAPTER 4 INFERENCES ABOUT PROCESS QUALITY
Confidence intervals on means, unknown Sampling distribution

variance(s)
Confidence intervals on proportions Scaled residuals
Confidence intervals on the variance of a normal Statistic
distribution
Confidence intervals on the variances of two t-distribution
normal distributions
Critical region for a test statistic Test statistic
F-distribution Tests of hypotheses on means, known variance(s)
Hypothesis testing Tests of hypotheses on means, unknown
variance(s)
Least squares estimator Tests of hypotheses on proportions
Linear statistical model Tests of hypotheses on the variance of a normal
distribution
Minimum variance estimator Tests of hypotheses on the variances of two
normal distributions
Null hypothesis Type I error
P-value Type II error
P-value approach Unbiased estimator
Parameters of a distribution
CHAPTER 4 INFERENCES ABOUT PROCESS QUALITY 4-3
EXERCISES
Note: New exercises are noted with .
4.1. 
Suppose that you are testing the following hypotheses where the variance is known:
H0 :   100
H1 :   100
Find the P-value for the following values of the test statistic.
(a) Z0 = 2.75
From Appendix II, (Z0) = (2.75) = 0.99702

For a two-sided test: P = 2[1 − (|Z0|)] = 2[1 – 0.99702] = 0.00596
(b) Z0 = 1.86

(c) Z0 = −2.05
From Appendix II, (Z0) = (|−2.05|) = (2.05) = 0.97982

For a two-sided test: P = 2[1 - (|Z0|)] = 2[1 – 0.97982] = 0.04036
(d) Z0 = −1.86
Same answer as for (b)

From Appendix II, (Z0) = (|−1.86|) = (1.86) = 0.96856
4.2. 
H0 :   100
H1 :   100
(a) Z0 = 2.60

For a one-sided, upper-tail test: P = 1 − (Z0) = 1 – 0.99534 = 0.00466
(b) Z0 = 1.85

For a one-sided, upper-tail test: P = 1 − (Z0) = 1 – 0. 96784 = 0.03216
(c) Z0 = 2.15

(d) Z0 = 3.72

4.3. 
H0 :   100
H1 :   100
(a) Z0 = −2.35

For a one-sided, lower-tail test and by symmetry of the normal distribution:
P = (Z0) = (−2.35) = 1 − (2.35) = 1 – 0.99061 = 0.00939
(b) Z0 = −1.99

P = (Z0) = (−1.99) = 1 − (1.99) = 1 – 0. 97670 = 0.02330
(c) Z0 = −2.18

P = (Z0) = (−2.18) = 1 − (2.18) = 1 – 0. 98537 = 0.01463
(d) Z0 = −1.85

P = (Z0) = (−1.85) = 1 − (1.85) = 1 – 0. 96784 = 0.03216
4.4. 
Suppose that you are testing the following hypotheses where the variance is unknown:
H0 :   100
H1 :   100
The sample size is n = 10. Find bounds on the P-value for the following values of the test statistic.
(a) t0 = 2.75
From Appendix IV and ν = n – 1 = 10 – 1 =9,

 0.025 0.01
T , 9 2.262 2.75 2.821
For a two-sided test: 2(0.01) < P < 2(0.025), or 0.02 < P < 0.05
(b) t0 = 1.86
From Appendix IV and ν = 9,

 0.05 0.025
T , 9 1.833 1.86 2.262
For a two-sided test: 2(0.025) < P < 2(0.05), or 0.05 < P < 0.10
(c) t0 = −2.05

 0.05 0.025
T , 9 1.833 2.05 2.262
For a two-sided test and by symmetry of the t distribution: 2(0.025) < P < 2(0.05), or 0.05 < P < 0.10
(d) t0 = −1.86
Same answer as for (b)

4.5. 
H0 :   100
H1 :   100
(a) t0 = 2.55
From Appendix IV and ν = n – 1 = 12 – 1 = 11,

 0.025 0.01
T , 11 2.20 2.55 2.718
For a one-sided, upper-tail test: 0.01 < P < 0.025
(b) t0 = 1.87

 0.05 0.025
T , 11 1.796 1.87 2.20
(c) t0 = 2.05

 0.05 0.025
T , 11 1.796 2.05 2.20
(d) t0 = 2.80

 0.01 0.005
T , 11 2.718 2.80 3.106
4.6. 
H0 :   100
H1 :   100
(a) t0 = −2.80
From Appendix IV and ν = n – 1 = 20 – 1 = 19,

 0.01 0.005
T , 19 2.539 2.80 2.861
For a one-sided, lower-tail test and by symmetry of the t distribution: 0.005 < P < 0.01
(b) t0 = −1.75

 0.05 0.025
T , 19 1.729 1.75 2.093
(c) t0 = −2.54

 0.01 0.005
T , 19 2.539 2.54 2.861
(d) t0 = −2.05

 0.05 0.025
T , 19 1.729 2.05 2.093
4.7.
The inside diameters of bearings used in an aircraft landing gear assembly are known to have a standard
deviation of  = 0.002 cm. A random sample of 15 bearings has an average inside diameter of
8.2535 cm.
(a) Test the hypothesis that the mean inside bearing diameter is 8.25 cm. Use a two-sided alternative
and  = 0.05.
Since  is known, use the standard normal distribution:

x ~ N(, ), n = 15, x = 8.2535 cm,  = 0.002 cm, 0 = 8.25,  = 0.05
Test H0:  = 8.25 vs. H1:   8.25. Reject H0 if |Z0|>Z/2.
x  0 8.2535  8.25
Z0    6.78 (Equation 4.23)
 n 0.002 15
Z/2 = Z0.05/2 = Z0.025 = 1.96 (from Appendix II)
Reject H0:  = 8.25, and conclude that the mean bearing ID is not equal to 8.25 cm.
(b) Find the P-value for this test.
From Appendix II, find the corresponding cumulative standard normal, (Z0) for Z0 = 6.78, and calculate:
P-value = 2[1  (Z0)] = 2[1  (6.78)] = 2[1  1.00000] = 0
(c) Construct a 95% two-sided confidence interval on the mean bearing diameter.
Construct a 95% two-sided confidence interval on mean bearing diameter.


x  Z /2    n
n    x  Z /2 

8.25  1.96 0.002 15     8.25  1.96  0.002 15  (Equation 4.29)
8.249    8.251
MTB > Stat > Basic Statistics > 1-Sample Z
One-Sample Z
The assumed standard deviation = 0.002
N Mean SE Mean 95% CI

15 8.23530 0.00052 (8.23429, 8.23631)
4.8.
The tensile strength of a fiber used in manufacturing cloth is of interest to the purchaser. Previous
experience indicates that the standard deviation of tensile strength is 2 psi. A random sample of eight
fiber specimens is selected, and the average tensile strength is found to be 127 psi.
(a) Test the hypothesis that the mean tensile strength equals 125 psi versus the alternative that the
mean exceeds 125 psi. Use  = 0.05.
0 = 125;  = 0.05
Test H0:  = 125 vs. H1:  > 125. Reject H0 if Z0 > Z.
x  0 127  125
Z0    2.828
 n 2 8
Z = Z0.05 = 1.645
Reject H0:  = 125, and conclude that the mean tensile strength exceeds 125 psi.
(b) What is the P-value for this test?
P-value = 1  (Z0) = 1  (2.828) = 1  0.99766 = 0.00234
(c) Discuss why a one-sided alternative was chosen in part (a).
In strength tests, we usually are interested in whether some minimum requirement is met, not simply
that the mean does not equal the hypothesized value. A one-sided hypothesis test lets us do this.
(d) Construct a 95% lower confidence interval on the mean tensile strength.
 n 
x  Z 
127  1.645  2 8   
125.8  
One-Sample Z
Test of mu = 125 vs > 125

The assumed standard deviation = 2
95% Lower
N Mean SE Mean Bound Z P
8 127.000 0.707 125.837 2.83 0.002
4.9.
The service life of a battery used in a cardiac pacemaker is assumed to be normally distributed. A
random sample of ten batteries is subjected to an accelerated life test by running them continuously at
an elevated temperature until failure, and the following lifetimes (in hours) are obtained: 25.5, 26.1,
26.8, 23.2, 24.2, 28.4, 25.0, 27.8, 27.3, and 25.7.
(a) The manufacturer wants to be certain that the mean battery life exceeds 25 h. What conclusions can
be drawn from these data (use = 0.05).
Since  is unknown, calculate the sample standard deviation S , and use the t-distribution, one-sided:
x ~ N(, ), n = 10, x = 26.0, s = 1.62, 0 = 25,  = 0.05
Test H0:  = 25 vs. H1:  > 25. Reject H0 if t0 > t.
t0   x  0  S 
n  26.0  25 1.62  
10  1.952 (Equation 4.33)
t, n1 = t0.05, 101 = 1.833 (from Appendix IV)

Reject H0:  = 25, and conclude that the mean life exceeds 25 h.
MTB > Stat > Basic Statistics > 1-Sample t
One-Sample T: Ex 4-9
95% Lower
Variable N Mean StDev SE Mean Bound T P
Ex 4-9 10 26.000 1.625 0.514 25.058 1.95 0.042
(b) Construct a 90% two-sided confidence interval on mean life in the accelerated test.
Construct a 90% two-sided confidence interval on mean life in the accelerated test.  = 0.10
x  t /2,n1 S n    x  t /2,n1 S n

26.0  1.833 1.62 
10    26.0  1.833 1.62  10  (Equation 4.34)
25.06    26.94
4.9.(b) continued
Test of mu = 25 vs not = 25
Variable N Mean StDev SE Mean 90% CI T P

Ex 4-9 10 26.000 1.625 0.514 (25.058, 26.942) 1.95 0.083
(c) Construct a normal probability plot of the battery life data. What conclusions can you draw?
MTB > Graph > Probability Plot > Single and ensure Distribution = Normal
Probability Plot of Ex 4-9
The plotted points fall approximately along a straight line, so the assumption that battery life is normally
distributed is appropriate.
4.10.
Using the data from Exercise 4.7, construct a 95% lower confidence interval on mean battery life. Why
would the manufacturer be interested in a one-sided confidence interval?
x ~ N(, ); n = 10; x = 26.0 h; s = 1.62 h;  = 0.05; t, n1 = t0.05,9 = 1.833

x  t ,n 1 S  n 

26.0  1.833 1.62 10   
25.06  
The manufacturer might be interested in a lower confidence interval on mean battery life when
establishing a warranty policy.
4.11.
A new process has been developed for applying photoresist to 125-mm silicon wafers used in
manufacturing integrated circuits. Ten wafers were tested, and the following photoresist thickness
measurements ( in angstromx  1000) were observed: 13.3987, 13.3957, 13.3902, 13.4015, 13.4001,
13.3918, 13.3965, 13.3925, 13.3946, and 13.4002.
(a) Test the hypothesis that mean thickness is 13.4  1000 Å. Use  = 0.05 and assume a two-sided
alternative.
Since  is unknown, calculate the sample standard deviation S , and use the t-distribution:
x ~ N(, ), n = 10, x = 13.39618  1000 Å, s = 0.00391, 0 = 13.4  1000 Å,  = 0.05
Test H0:  = 13.4 vs. H1:   13.4. Reject H0 if |t0|>t/2.
t0   x  0  S  
n  13.39618  13.4  0.00391 
10  3.089 (Equation 4.33)
t/2, n1 = t0.025, 9 = 2.262 (from Appendix IV)
Reject H0:  = 13.4, and conclude that the mean thickness differs from 13.4  1000 Å.
Test of mu = 13.4 vs not = 13.4

Ex 4-11 10 13.3962 0.0039 0.0012 (13.3934, 13.3990) -3.09 0.013
4.11. continued
(b) Find a 99% two-sided confidence interval on mean photoresist thickness. Assume that thickness is
normally distributed.
 = 0.01

x  t /2,n1 S   n
n    x  t /2,n1 S

13.39618  3.2498 0.00391 10     13.39618  3.2498  0.00391 10  (Equation 4.34)
13.39216    13.40020
Test of mu = 13.4 vs not = 13.4

Ex 4-11 10 13.3962 0.0039 0.0012 (13.3922, 13.4002) -3.09 0.013
(c) Does the normality assumption seem reasonable for these data?
The plotted points form a reverse-“S” shape, instead of a straight line, so the assumption that battery
life is normally distributed is not appropriate.
4.12.
A machine is used to fill containers with a liquid product. Fill volume can be assumed to be normally
distributed. A random sample of ten containers is selected, and the net contents (oz) are as follows:
12.03, 12.01, 12.04, 12.02, 12.06, 11.98, 11.97, 12.02, 12.05, and 11.99.
(a) Suppose that the manufacturer wants to be sure that the mean net contents exceeds 12 oz. What
conclusions can be drawn from the data (use  = 0.01).
x ~ N(, ), 0 = 12,  = 0.01

n = 10, x = 12.017, s = 0.0298
Test H0:  = 12 vs. H1:  > 12. Reject H0 if t0 > t.
x  0 12.017  12
t0    1.8040
S n 0.0298 10
t/2, n1 = t0.005, 9 = 3.250
Do not reject H0:  = 12, and conclude that there is not enough evidence that the mean fill volume
exceeds 12 oz.
99% Lower
Variable N Mean StDev SE Mean Bound T P
Ex 4-12 10 12.0170 0.0298 0.0094 11.9904 1.80 0.053
(b) Construct a 99% two-sided confidence interval on the mean fill volume.
 = 0.01
t/2, n1 = t0.005, 9 = 3.250

x  t /2,n1 S   n
n    x  t /2,n1 S

12.017  3.250 0.0298 10     12.017  3.250  0.0298 10 
11.9864    12.0476
4.12. (b) continued

Ex 4-12 10 12.0170 0.0298 0.0094 (11.9863, 12.0477) 1.80 0.105
(c) Does the assumption of normality seem appropriate for the fill volume data?
The plotted points fall approximately along a straight line, so the assumption that fill volume is normally
distributed is appropriate.
4.13.
Ferric chloride is used as a flux in some types of extraction metallurgy processes. This material is shipped
in containers, and the container weight varies. It is important to obtain an accurate estimate of mean
container weight. Suppose that from long experience a reliable value for the standard deviation of flux
container weight is determined to be 4 lb. How large a sample would be required to construct a 95%
two-sided confidence interval on the mean that has a total width of 1 lb?
 = 4 lb,  = 0.05, Z/2 = Z0.025 = 1.9600, total confidence interval width = 1 lb, find n
 
2  Z /2  
n   total width

2 1.9600 4
  
n  1

n  246
4.14.
The diameters of aluminum alloy rods produced on an extrusion machine are known to have a standard
deviation of 0.0001 in. A random sample of 20 rods has an average diameter of 0.5021 in.
(a) Test the hypothesis that mean rod diameter is 0.5025 in. Assume a two-sided alternative and use
 = 0.05.
x ~ N(, ), 0 = 0.5025,  = 0.05

n = 20, x = 0.5021 in,  = 0.0001 in
Test H0:  = 0.5025 vs. H1:   0.5025. Reject H0 if |Z0| > Z/2.
x  0 0.5021  0.5025
Z0    17.89
 n 0.0001 20
Z/2 = Z0.05/2 = Z0.025 = 1.96
Reject H0:  = 0.5025, and conclude that the mean rod diameter differs from 0.5025.
One-Sample Z
Test of mu = 0.5025 vs not = 0.5025

The assumed standard deviation = 0.0001
N Mean SE Mean 95% CI Z P

20 0.502100 0.000022 (0.502056, 0.502144) -17.89 0.000
P-value = 2[1  (Z0)] = 2[1  (|−17.89|)] = 2[1  1] = 0
(c) Construct a 95% two-sided confidence interval on the mean rod diameter.

x  Z /2    n
n    x  Z /2 

0.5021  1.960 0.0001 20     0.5021  1.960  0.0001 20 
0.50206    0.50214
4.15.
The output voltage of a power supply is assumed to be normally distributed. Sixteen observations taken
at random on voltage are as follows: 10.35, 9.30, 10.00, 9.96, 11.65, 12.00, 11.25, 9.58, 11.54, 9.95,
10.28, 8.37, 10.44, 9.25, 9.38, and 10.85.
(a) Test the hypothesis that the mean voltage equals 12 V against a two-sided alternative using  = 0.05.
x ~ N(, ), n = 16, x = 10.259 V, s = 0.999 V, 0 = 12,  = 0.05

Test H0:  = 12 vs. H1:   12. Reject H0 if |t0|>t/2.

t0   x  0  S  
n  10.259  12 0.999 
16  6.971 (Equation 4.33)
t/2, n1 = t0.025, 15 = 2.131 (from Appendix IV)
Reject H0:  = 12, and conclude that the mean output voltage differs from 12V.

Ex 4-15 16 10.259 0.999 0.250 (9.727, 10.792) -6.97 0.000
(b) Construct a 95% two-sided confidence interval on .
Construct a 95% two-sided confidence interval on .


x  t /2,n1 S   n
n    x  t /2,n1 S
10.259  2.131 0.999 16     10.259  2.131  0.999 16  (Equation 4.34)

9.727    10.792
(c) Test the hypothesis that 2 = 11 using  = 0.05.
Test H0:  2 = 1 vs. H1:  2  1. Reject H0 if  20> 2/2, n-1 or 20 <  21-/2, n-1.
(16  1)0.9992
02  (n  1)S 2  02   14.970 (Equation 4.38)
1
2/2, n1 = 20.025,161 = 27.488 (from Appendix III)
21/2, n1 = 20.975,161 = 6.262 (from Appendix III)
Do not reject H0:  2 = 1, and conclude that there is insufficient evidence that the variance differs from 1.
14.15 continued
(d) Construct a 95% two-sided confidence interval on .
(n  1)S 2 2 /2,n1   2  (n  1)S 2 12 /2,n 1

(16  1)0.9992 27.488   2  (16  1)0.9992 6.262
(Equation 4.39)
0.545   2  2.391
0.738    1.546
Since the 95% confidence interval on  contains the hypothesized value,  02 = 1, the null hypothesis,
H0:  2 = 1, cannot be rejected. Using MINITAB:
MTB > Stat > Basic Statistics > Graphical Summary
Summary for Ex 4-15
(e) Construct a 95% upper confidence interval on .
  0.05; 12 ,n1  0.95,15

2
 7.2609 (from Appendix III)
 2  (n  1)S 2 12 ,n1
 2  (16  1)0.9992 7.2609 (Equation 4.40)
 2  2.062
  1.436
14.15 continued
(f) Does the assumption of normality seem reasonable for the output voltage?
Looking at the plot, the plotted points fall approximately along a straight line, so the assumption of a
normal distribution for output voltage seems appropriate.
4.16.
Two machines are used for filling glass bottles with a soft-drink beverage. The filling processes have
known standard deviations 1 = 0.010 liter and 2 = 0.005 liter, respectively. A random sample of n1 = 25
bottles from machine 1 and n2 = 15 bottles from machine 2 results in average net contents of x1 = 2.03
liters and x2 = 2.07 liters.
(a) Test the hypothesis that both machines fill to the same net contents, using  = 0.05. What are your
conclusions?
 = 0.05,  0 = 0
Test H0: 1 – 2 = 0 versus H0: 1 – 2  0. Reject H0 if Z0 > Z/2 or Z0 < –Z/2.
(x1  x2 )  0 (2.03  2.07)  0
Z0    16.80
 n1   n2
2
1
2
2 0.0102 25  0.0052 15
Z/2 = Z0.05/2 = Z0.025 = 1.96 Z/2 = 1.96
Reject H0: 1 – 2 = 0, and conclude that there is a difference in mean net contents between machine 1
and machine 2.
P-value = 2[1  (Z0)] = 2[1  (16.80)] = 2[1  1.00000] = 0
(c) Construct a 95% confidence interval on the difference in mean fill volume.
(x1  x2 )  Z /2
 12 
 22  (1   2 )  (x1  x2 )  Z /2
 12 
 22
n1 n2 n1 n2
2 2 2 2
(2.03  2.07)  1.9600 0.010  0.005  (1   2 )  (2.03  2.07)  1.9600 0.010  0.005
25 15 25 15
0.045  (1   2 )  0.035
The confidence interval for the difference does not contain zero. We can conclude that the machines do
not fill to the same volume.
4.17.
Two quality control technicians measured the surface finish of a metal part, obtaining the data in Table
4E.1. Assume that the measurements are normally distributed.
(a) Test the hypothesis that the mean surface finish measurements made by the two technicians are
equal. Use  = 0.05 and assume equal variances.
Test H0: 1  2 = 0 vs. H1: 1  2  0. Reject H0 if |t0|>t/2, n1+n2-2.

(n1  1)s12  (n2  1)s22 (7  1)0.1152  (8  1)0.1252
sP    0.1204
n1  n2  2 7 8 2 (Equations 4.51 and 4.52)
t0   x1  x2  s
P   
1 n1  1 n2  1.383  1.376  0.1204 1 7  1 8  0.11
t/2, n1+n2-2 = t0.025, 13 = 2.160 (from Appendix IV)
Do not reject H0, and conclude that there is not sufficient evidence of a difference between
measurements obtained by the two technicians.
Two-Sample T-Test and CI: Ex4-17T1, Ex4-17T2
Two-sample T for Ex4-17T1 vs Ex4-17T2
N Mean StDev SE Mean

Ex4-17T1 7 1.383 0.115 0.043
Ex4-17T2 8 1.376 0.125 0.044
Difference = mu (Ex4-17T1) - mu (Ex4-17T2)

Estimate for difference: 0.0066
95% CI for difference: (-0.1280, 0.1412)
T-Test of difference = 0 (vs not =): T-Value = 0.11 P-Value = 0.917 DF = 13
Both use Pooled StDev = 0.1204
4.17. continued
(b) What are the practical implications of the test in part (a)? Discuss what practical conclusions you
would draw if the null hypothesis were rejected.
The practical implication of this test is that it does not matter which technician measures parts; the
readings will be the same. If the null hypothesis had been rejected, we would have been concerned that
the technicians obtained different measurements, and an investigation should be undertaken to
understand why.
(c) Assuming that the variances are equal, construct a 95% confidence interval on the mean difference in
surface-finish measurements.
n1 = 7, x1 = 1.383, s1 = 0.115; n2 = 8, x2 = 1.376, s2 = 0.125, sP = 0.120

 = 0.05, t/2, n1+n22 = t0.025, 13 = 2.160
(x1  x2 )  t /2,n s 1 n1  1 n2  (1   2 )  (x1  x2 )  t /2,n s 1 n1  1 n2
1  n2 2 p 1  n2 2 p
(1.383  1.376)  2.1604(0.120) 1 7  1 8  (1   2 )  (1.383  1.376)  2.1604(0.120) 1 7  1 8

0.127  (1   2 )  0.141
(Equation 4.56)
The confidence interval for the difference contains zero. We can conclude that there is not sufficient
evidence of a difference in measurements obtained by the two technicians.
(d) Test the hypothesis that the variances of the measurements made by the two technicians are equal.
Use What are the practical implications if the null hypothesis is rejected?
Test H0 :  12   22 versus H1 :  12   22 .
Reject H0 if F0  F /2,n or F0  F1 /2,n .
1 1,n2 1 1 1, n2 1
F0  S12 S22  0.1152 0.1252  0.8464

F /2,n  F0.05/2,71,8 1  F0.025,6,7  5.119
1 1,n2 1
F1 /2,n  F10.05/2,71,81  F0.975,6,7  0.176

1 1,n2 1
4.17.(d) continued
MTB > Stat > Basic Statistics > 2 Variances
Test and CI for Two Variances: Ex4-17T1, Ex4-17T2
Method
Null hypothesis Sigma(Ex4-17T1) / Sigma(Ex4-17T2) = 1
Alternative hypothesis Sigma(Ex4-17T1) / Sigma(Ex4-17T2) not = 1
Significance level Alpha = 0.05
Statistics
Variable N StDev Variance
Ex4-17T1 7 0.115 0.013
Ex4-17T2 8 0.125 0.016
Ratio of standard deviations = 0.920

Ratio of variances = 0.846
95% Confidence Intervals
CI for
Distribution CI for StDev Variance
of Data Ratio Ratio
Normal (0.406, 2.195) (0.165, 4.816)
Continuous (0.389, 3.092) (0.151, 9.562)
Tests
Test
Method DF1 DF2 Statistic P-Value
F Test (normal) 6 7 0.85 0.854
Levene's Test (any continuous) 1 13 0.01 0.920
Do not reject H0, and conclude that there is not sufficient evidence of a difference in variability between
measurements obtained by the two technicians. If the null hypothesis is rejected, we would have been
concerned about the difference in measurement variability between the technicians, and an
investigation should be undertaken to understand why.
(e) Construct a 95% confidence interval estimate of the ratio of the variances of technician
measurement error.
F1 /2,n  F0.975,7,6  0.1954; F /2,n  F0.025,7,6  5.6955

2 1,n1 1 2 1, n1 1
S12  12 S12
F1 /2,n2 1,n1 1   F /2,n 1,n 1
S22  22 S22 2 1
0.1152  12 0.1152
(0.1954)   (5.6955)
0.1252  22 0.1252
 12
0.165   4.821
 22
4.17. continued
(f) Construct a 95% confidence interval on the variance of measurement error for technician 2.
n2  8; x2  1.376; S2  0.125
  0.05; 2 /2,n   0.025,7
2
 16.0128; 12 /2,n  0.975,7
2
 1.6899
2 1 2 1
(n  1)S 2 (n  1)S 2
 2 
2 /2,n1 12 /2,n1
(8  1)0.1252 (8  1)0.1252
 2 
16.0128 1.6899
0.007    0.065
2
(g) Does the normality assumption seem reasonable for the data?
MTB > Graph > Probability Plot > Multiple and ensure Distribution = Normal
Probability Plot of Ex4-17T1, Ex4-17T2
The normality assumption seems reasonable for both of these readings.

4.18.
Suppose that x1 ~ N(1, 12) and x2 ~ N(2, 22), and that x1 and x2 are independent. Develop a procedure
for constructing a 100(1 − )% confidence interval on 1 − 2, assuming that 12 and 22 are unknown
and cannot be assumed equal.
From Eqn. 4.54 and 4.55, for  12   22 and both unknown, the test statistic is
t 
* x1  x2
with degrees of freedom  
2
S 2
1
2
n1  S22 n2
   
0
S12 n1  S22 n2 2 22 2
S n S n 1 1 2 2
 n1  1  n2  1
A 100(1-)% confidence interval on the difference in means would be:

(x1  x2 )  t /2, S12 n1  S22 n2  (1  2 )  (x1  x2 )  t /2, S12 n1  S22 n2
4.19.
Two different hardening processes—(1) saltwater quenching and (2) oil quenching—are used on
samples of a particular type of metal alloy. The results are shown in Table 4E.2. Assume that hardness is
normally distributed.
Saltwater quench: n1 = 10, x1 = 147.6, s1 = 4.97; Oil quench: n2 = 10, x2 = 149.4, s2 = 5.46
14.19 continued
(a) Test the hypothesis that the mean hardness for the saltwater quenching process equals the mean
hardness for the oil quenching process. Use  = 0.05 and assume equal variances.
Test H0: 1  2 = 0 vs. H1: 1  2  0. Reject H0 if |t0|>t/2, n1+n2-2.

(n1  1)s12  (n2  1)s22 (10  1)4.972  (10  1)5.462
sP    5.2217
n1  n2  2 10  10  2 (Eqns 4.51 and 4.52)
t0   x1  x2  sP  
1 n1  1 n2  147.60  149.40  5.2217 1 10  1 10  0.77 
t/2, n1+n2-2 = t0.025, 18 = 2.101 (from Appendix IV)
Do not reject H0, and conclude that there is not sufficient evidence of a difference between
measurements produced by the two hardening processes.
Two-Sample T-Test and CI: Ex4-19SQ, Ex4-19OQ
Two-sample T for Ex4-19SQ vs Ex4-19OQ

Ex4-19SQ 10 147.60 4.97 1.6
Ex4-19OQ 10 149.40 5.46 1.7
Difference = mu (Ex4-19SQ) - mu (Ex4-19OQ)

Estimate for difference: -1.80
T-Test of difference = 0 (vs not =): T-Value = -0.77 P-Value = 0.451 DF = 18
(b) Assuming that the variances 12 and 22 are equal, construct a 95% confidence interval on the
difference in mean hardness.
 = 0.05, t/2, n1+n22 = t0.025, 18 = 2.1009

(x1  x2 )  t /2,n S 1 n1  1 n2  (1   2 )  (x1  x2 )  t /2,n S 1 n1  1 n2
1  n2 2 p 1  n2 2 p
(147.6  149.4)  2.1009(5.22) 1 10  1 10  (1   2 )  (147.6  149.4)  2.1009(5.22) 1 10  1 10

6.7  (1   2 )  3.1
(Eqn 4.56)
The confidence interval for the difference contains zero. We conclude that there is not sufficient
evidence of a difference between measurements produced by the two hardening processes.
(c) Construct a 95% confidence interval on the ratio 12 / 22. Does the assumption made earlier of
equal variances seem reasonable?
F1 /2,n  F0.975,9,9  0.2484; F /2,n  F0.025,9,9  4.0260

2 1,n1 1 2 1,n1 1
S12  12 S12
F1 /2,n2 1,n1 1   F /2,n 1,n 1
S22  22 S22 2 1
4.972  12 4.972
(0.2484)   (4.0260)
5.462  22 5.462
 12
0.21   3.34
 22
Test and CI for Two Variances: Ex4-19SQ, Ex4-19OQ
Method
Null hypothesis Sigma(Ex4-19SQ) / Sigma(Ex4-19OQ) = 1

Alternative hypothesis Sigma(Ex4-19SQ) / Sigma(Ex4-19OQ) not = 1
Statistics
Ex4-19SQ 10 4.971 24.711
Ex4-19OQ 10 5.461 29.822


CI for
of Data Ratio Ratio
Normal (0.454, 1.826) (0.206, 3.336)
Continuous (0.390, 2.157) (0.152, 4.652)
Tests
Test
F Test (normal) 9 9 0.83 0.784
Levene's Test (any continuous) 1 18 0.08 0.783
Since the confidence interval includes the ratio of 1, the assumption of equal variances seems
reasonable.
(d) Does the assumption of normality seem appropriate for these data?
MTB > Graph > Probability Plot > Multiple and ensure Distribution = Normal
Probability Plot of Ex4-19SQ, Ex4-19OQ
The normal distribution assumptions for both the saltwater and oil quench methods seem reasonable.
However, the slopes on the normal probability plots do not appear to be the same, so the assumption of
equal variances does not seem reasonable.
4.20.
A random sample of 200 printed circuit boards contains 15 defective or nonconforming units. Estimate
the process fraction nonconforming.
(a) Test the hypothesis that the true fraction nonconforming in this process is 0.10. Use  = 0.05. Find
the P-value.
p0 = 0.10,  = 0.05. Test H0: p = 0.10 versus H1: p  0.10. Reject H0 if |Z0| > Z/2.
np0 = 200(0.10) = 20
Since (x = 15) < (np0 = 20), use the normal approximation to the binomial for x < np0.
(x  0.5)  np0 (15  0.5)  20
Z0    1.0607 (Eqn 4.43)
np0 (1  p0 ) 20(1  0.10)
Z/2 = Z0.05/2 = Z0.025 = 1.96
Do not reject H0, and conclude that the sample process fraction nonconforming does not differ from
0.10.
P-value = 2[1  |Z0|] = 2[1  |1.0607|] = 2[1  0.8556] = 0.2888
MTB > Stat > Basic Statistics > 1 Proportion

Under Option, select to Use test and interval based on normal distribution
Test and CI for One Proportion
Test of p = 0.1 vs p not = 0.1
Sample X N Sample p 95% CI Z-Value P-Value

1 15 200 0.075000 (0.038496, 0.111504) -1.18 0.239
Using the normal approximation.

Note that MINITAB does not use the continuity correction factor (+/- 0.5 in Eqn 4.43) in computing the
test statistic.
(b) Construct a 95% two-sided confidence interval on the true fraction nonconforming in the production
process.
 = 0.05, Z/2 = Z0.05/2 = Z0.025 = 1.96

pˆ  Z /2 pˆ(1  pˆ) n  p  pˆ  Z /2 pˆ(1  pˆ) n
0.075  1.96 0.075(1  0.075) 200  p  0.075  1.96 0.075(1  0.075) 200
0.038  p  0.112
4.21.
A random sample of 500 connecting rod pins contains 65 nonconforming units. Estimate the process
fraction nonconforming.
(a) Test the hypothesis that the true fraction defective in this process is 0.08. Use  = 0.05.
Test H0: p = 0.08 versus H1: p  0.08. Reject H0 if |Z0|>Z/2.
np0 = 500(0.08) = 40
Since (x = 65)>(np0 = 40), use the normal approximation to the binomial for x>np0.
(x  0.5)  np0 (65  0.5)  40
Z0    4.0387
np0 (1  p0 ) 40(1  0.08)
Z/2 = Z0.05/2 = Z0.025 = 1.96
Reject H0, and conclude the sample process fraction nonconforming differs from 0.08.
MTB > Stat > Basic Statistics > 1 Proportion

Under Option, select to Use test and interval based on normal distribution
Test and CI for One Proportion
Test of p = 0.08 vs p not = 0.08
Sample X N Sample p 95% CI Z-Value P-Value

1 65 500 0.130000 (0.100522, 0.159478) 4.12 0.000
Using the normal approximation.

Note that MINITAB does not use the continuity correction factor (+/- 0.5 in Eqn 4.43) in computing the
test statistic.

Find the corresponding cumulative standard normal, (Z0) for Z0 = 4.0387, and calculate:
P-value = 2[1  |Z0|] = 2[1  |4.0387|] = 2[1  0.99997] = 0.00006
(c) Construct a 95% upper confidence interval on the true process fraction nonconforming.
 = 0.05, Z = Z0.05 = 1.645
p  pˆ  Z pˆ(1  pˆ) n
p  0.13  1.645 0.13(1  0.13) 500
p  0.155
The 95% upper confidence interval for the process fraction nonconforming is 0.155.
4.22.
Two processes are used to produce forgings used in an aircraft wing assembly. Of 200 forgings selected
from process 1, 10 do not conform to the strength specifications, whereas of 300 forgings selected from
process 2, 20 are nonconforming.
(a) Estimate the fraction nonconforming for each process.

n1 = 200, x1 = 10, p̂1 = x1/n1 = 10/200 = 0.05
n2 = 300, x2 = 20, p̂2 = x2/n2 = 20/300 = 0.067
(b) Test the hypothesis that the two processes have identical fractions nonconforming. Use  = 0.05.
Test H0: p1 = p2 versus H1: p1  p2. Reject H0 if Z0 > Z/2 or Z0 < –Z/2
x x 10  20 pˆ1  pˆ2 0.05  0.067
pˆ  1 2   0.06 Z0    0.7842
n1  n2 200  300 pˆ(1  pˆ) 1 n1  1 n2  0.06(1  0.06) 1 200  1 300 
Z/2 = Z0.05/2 = Z0.025 = 1.96; Z/2 = 1.96
Do not reject H0. Conclude there is no strong evidence to indicate a difference between the fraction
nonconforming for the two processes.
MTB > Stat > Basic Statistics > 2 Proportions
Test and CI for Two Proportions
Sample X N Sample p
1 10 200 0.050000
2 20 300 0.066667
Difference = p (1) - p (2)

Test for difference = 0 (vs not = 0): Z = -0.77 P-Value = 0.442
Fisher's exact test: P-Value = 0.565
(c) Construct a 90% confidence interval on the difference in fraction nonconforming between the two
processes.
pˆ1 (1  pˆ1 ) pˆ2 (1  pˆ2 ) pˆ1 (1  pˆ1 ) pˆ2 (1  pˆ2 )
(pˆ1  pˆ2 )  Z /2   (p1  p2 )  (pˆ1  pˆ2 )  Z /2 
n1 n2 n1 n2
0.05(1  0.05) 0.067(1  0.067) 0.05(1  0.05) 0.067(1  0.067)

(0.050  0.067)  1.645   ( p1  p2 )  (0.05  0.067)  1.645 
200 300 200 300
0.052  (p1  p2 )  0.018
4.23.
A new purification unit is installed in a chemical process. Before its installation, a random sample yielded
the following data about the percentage of impurity: x12  9.85, s12  6.79 and n1  10 . After installation,
a random sample resulted in x22  8.08, s22  6.18 and n2  8 .
(a) Can you conclude that the two variances are equal? Use  =0.05.
Test H0 :  12   22 versus H1 :  12   22 , at   0.05

Reject H0 if F0  F /2,n1 1,n2 2 or F0  F1 /2,n1 1,n2 1
F /2,n1 1,n2 2  F0.025,9,7  4.8232; F1 /2,n1 1,n2 1  F0.975,9,7  0.2383
F0  S12 S22  6.79 6.18  1.0987
F0  1.0987  4.8232 and  0.2383, so do not reject H0
s12  6.79  2.606; s22  6.18  2.486
Test and CI for Two Variances
Method
Null hypothesis Sigma(1) / Sigma(2) = 1

Alternative hypothesis Sigma(1) / Sigma(2) not = 1
Statistics
Sample N StDev Variance
1 10 2.606 6.790
2 8 2.486 6.180


CI for
of Data Ratio Ratio
Normal (0.477, 2.147) (0.228, 4.611)
Tests
Test
F Test (normal) 9 7 1.10 0.922
The impurity variances before and after installation are the same.
4.23. continued
(b) Can you conclude that the new purification device has reduced the mean percentage of impurity?
Use  = 0.05.
Test H0: 1 = 2 versus H1: 1>2,  = 0.05.

Reject H0 if t0>t,n1+n22.
t,n1+n22 = t0.05, 10+82 = 1.746
 n1  1 S12   n2  1 S22 10  1 6.79  8  1 6.18
SP    2.554
n1  n2  2 10  8  2
x1  x2 9.85  8.08
t0    1.461
SP 1 n1  1 n2 2.554 1 10  1 8
The mean impurity after installation of the new purification unit is not less than before.
Two-Sample T-Test and CI
Sample N Mean StDev SE Mean

1 10 9.85 2.61 0.82
2 8 8.08 2.49 0.88
Difference = mu (1) - mu (2)

Estimate for difference: 1.77
95% lower bound for difference: -0.35
T-Test of difference = 0 (vs >): T-Value = 1.46 P-Value = 0.082 DF = 16
4.24.
Two different types of glass bottles are suitable for use by a soft-drink beverage bottler. The internal
pressure strength of the bottle is an important quality characteristic. It is known that 1 = 2 = 2.5 psi.
From a random sample of n1 = n2 = 15 bottles, the mean pressure strengths are observed to be
x1 = 175.9 psi and x2 = 181.2 psi. The company will not use bottle design 2 unless its pressure strength
exceeds that of bottle design 1 by at least 5 psi. Based on the sample data, should they use bottle design
2 if we use  = 0.05. What is the P-value for this test?
Want to demonstrate that 2 is greater than 1 by at least 5 psi, so H1: 1 + 5 < 2. So test a difference
0 = 5, test H0: 1  2 =  5 versus H1: 1  2 <  5.
Reject H0 if Z0 <  Z .
0 = 5 Z = Z0.05 = 1.645

 x1  x2   0 (175.9  181.2)  (5)
Z0    0.3286
 n1   n2
2
1
2
2 2.52 15  2.52 15
(Z0 = 0.3286) > 1.645, so do not reject H0.
The mean strength of Design 2 does not exceed Design 1 by 5 psi.
P-value = (Z0) = (0.3286) = 0.3712
Two-Sample T-Test and CI
Sample N Mean StDev SE Mean

1 15 175.90 2.50 0.65
2 15 181.20 2.50 0.65
Difference = mu (1) - mu (2)

95% upper bound for difference: -3.747
T-Test of difference = -5 (vs <): T-Value = -0.33 P-Value = 0.372 DF = 28
Note: For equal variances and sample sizes, the Z-value is the same as the t-value. The P-values are
close due to the sample sizes.
4.25.
The diameter of a metal rod is measured by 12 inspectors, each using both a micrometer caliper and a
vernier caliper. The results are shown in Table 4E.3. Is there a difference between the mean
measurements produced by the two types of caliper? Use  = 0.01.
Test H0: d = 0 versus H1: d  0. Reject H0 if |t0|>t/2, n1 + n2  2.

n
d 1
n  xMicrometer, j  xVernier, j   1
12 
 0.150  0.151    0.151  0.152   0.000417
j 1
2
n  n 
 d   dj 
2
j n
Sd 
2 j 1  j 1   0.0013112
 n  1
t0  d Sd  
n  0.000417 0.001311  
12  1.10
t/2, n1 + n2  2 = t0.005,22 = 2.8188
(|t0| = 1.10) < 2.8188, so do not reject H0. There is no strong evidence to indicate that the two calipers
differ in their mean measurements.
MTB > Stat > Basic Statistics > Paired t
Paired T-Test and CI: Ex4-25MC, Ex4-25VC
Paired T for Ex4-25MC - Ex4-25VC

Ex4-25MC 12 0.151167 0.000835 0.000241
Ex4-25VC 12 0.151583 0.001621 0.000468
Difference 12 -0.000417 0.001311 0.000379
95% CI for mean difference: (-0.001250, 0.000417)

T-Test of mean difference = 0 (vs not = 0): T-Value = -1.10 P-Value = 0.295
4.26.
The cooling system in a nuclear submarine consists of an assembly pipe through which a coolant is
circulated. Specifications require that weld strength must meet or exceed 150 psi.
(a) Suppose the designers decide to test the hypothesis H0:  = 150 versus H1:  > 150. Explain why this
choice of alternative is preferable to H1:  < 150
The alternative hypothesis H1:  > 150 is preferable to H1:  < 150 we desire a true mean weld strength
greater than 150 psi. In order to achieve this result, H0 must be rejected in favor of the alternative H1, 
> 150.
(b) A random sample of 20 welds results in x = 153.7 psi and s = 11.5 psi. What conclusions can you
draw about the hypothesis in part (a)? Use  = 0.05.
Test H0:  = 150 versus H1:  > 150. Reject H0 if t0 > t, n 1. t, n 1 = t0.05,19 = 1.7291.

t0   x    S  
n  153.7  150  11.5 
20  1.4389
(t0 = 1.4389) < 1.7291, so do not reject H0. There is insufficient evidence to indicate that the mean
strength is greater than 150 psi.
One-Sample T
95% Lower
N Mean StDev SE Mean Bound T P
20 153.70 11.50 2.57 149.25 1.44 0.083
4.27.
An experiment was conducted to investigate the filling capability of packaging equipment at a winery in
Newberg, Oregon. Twenty bottles of Pinot Gris were randomly selected and the fill volume (in ml)
measured. Assume that fill volume has a normal distribution. The data are as follows: 753, 751, 752,
753, 753, 753, 752, 753, 754, 754, 752, 751, 752, 750, 753, 755, 753, 756, 751, and 750.
(a) Do the data support the claim that the standard deviation of fill volume is less than 1 ml? Use  =
0.05.
n = 20, x = 752.6 ml, s = 1.5,  = 0.05
Test H0: 2 = 1 versus H1: 2 < 1. Reject H0 if 20 < 21-, n-1.
02  (n  1)S2   02  (20  1)1.52  1  42.75
21-, n-1 = 20.95,19 = 10.1170 (from Appendix III)
(20 = 42.75)>10.1170, so do not reject H0. The standard deviation of the fill volume is not less than 1ml.
MTB > Stat > Basic Statistics > 1 Variance
Test and CI for One Variance: Ex4-27
Method
Null hypothesis Sigma = 1

Alternative hypothesis Sigma < 1
The chi-square method is only for the normal distribution.

...
Statistics

Ex4-27 20 1.54 2.37
95% One-Sided Confidence Intervals

Upper
Bound
for Upper Bound
Variable Method StDev for Variance
Ex4-27 Chi-Square 2.11 4.44
...
Tests
Test
Variable Method Statistic DF P-Value
Ex4-27 Chi-Square 44.95 19 0.999
...
4.27. continued
(b) Find a 95% two-sided confidence interval on the standard deviation of fill volume.
2/2, n-1 = 20.025,19 = 32.85; 21-/2, n-1 = 20.975,19 = 8.91 (from Appendix III)
(n  1)S 2 2 /2,n1   2  (n  1)S 2 12 /2,n1
(20  1)1.52 32.85   2  (20  1)1.52 8.91
1.30   2  4.80
1.14    2.19
MTB > Stat > Basic Statistics > 1 Variance
Test and CI for One Variance: Ex4-27
Method
Null hypothesis Sigma = 1

Alternative hypothesis Sigma not = 1
The chi-square method is only for the normal distribution.

...
Statistics
Ex4-27 20 1.54 2.37

CI for CI for
Variable Method StDev Variance
Ex4-27 Chi-Square (1.17, 2.25) (1.37, 5.05)
...
Tests
Test
Variable Method Statistic DF P-Value
Ex4-27 Chi-Square 44.95 19 0.001
...
4.27.(b) continued
Also, in MINITAB
MTB > Stat > Basic Statistics > Graphical Summary
Summary for Ex4-27
The confidence interval does not include unity; therefore, we cannot conclude that the standard
deviation of fill volume is less than 1 ml.
4.27. continued
(c) Does it seem reasonable to assume that fill volume has a normal distribution?
Probability Plot of Ex4-27
The plotted points do not fall approximately along a straight line, so the assumption that battery life is
normally distributed is not appropriate.
4.28.
Suppose we wish to test the hypotheses
H0 :   25
H1 :   25
where we know that 2 = 16.0. If the true mean is really 30, what sample size must be used to ensure
that the probability of type II error is no greater than 0.10? Assume that  = 0.05.
What n is needed such that the Type II error, , is less than or equal to 0.10?
  1  2  30  25  5 d    5 16  1.25
From Figure 4.7, the operating characteristic curve for two-sided at  = 0.05, n = 7. Check:
      
   Z /2   n     Z /2   n    1.96  5 7 4   1.96  5 7 4 
 (1.3472)  (5.2672)  0.0890  0.0000  0.0890
MTB > Stat > Power and Sample Size > 1-Sample Z
Power and Sample Size
1-Sample Z Test
Testing mean = null (versus not = null)

Calculating power for mean = null + difference
Alpha = 0.05 Assumed standard deviation = 4
Sample Target
Difference Size Power Actual Power
5 7 0.9 0.911046
Power Curve for 1-Sample Z Test

4.29.
Consider the hypotheses
H0 :   0
H1 :   0
where 2 is known. Derive a general expression for determining the sample size for detecting a true
mean of 1  0 with probability 1 −  if the type I error is .
Let 1 = 0 + .
  
From equation. 4.46,    Z /2   n     Z /2   n  
 
If >0, then   Z /2   n  is likely to be small compared with . So,

   Z /2   n  

( )   1 Z /2   n  
 Z   Z /2   n 
2
n  (Z /2  Z  )  
4.30.
Sample size allocation. Suppose we are testing the hypotheses
H0 : 1  2
H1 : 1  2
where  12 and  22 are known. Resources are limited, and consequently the total sample size n1 + n2 = N.
How should we allocate the N observations between the two populations to obtain the most powerful
test?
x1  x2
Maximize: Z0  Subject to: n1  n2  N .
 n1   22 n2
2
1
Since (x1  x2 ) is fixed, an equivalent statement is

 12  22  12  22
Minimize: L    
n1 n2 n1 N  n1
dL   12  22  dL  1 2
n1  1   N  n1   22 
1
  
dn1  n1 N  n1  dn1  
 1n12 12  (1)(1)  N  n1   22  0
2
 12  22
  0
 N  n1 
2
n12
n1  1

n2  2
Allocate N between n1 and n2 according to the ratio of the standard deviations.

4.31.
Note: There is a typographical error in the hypotheses (should be 22) in early printings of the 7th
edition; this solution is for the correct hypotheses.
Develop a test for the hypotheses

H0 : 1  22
H1 : 1  22
where  12 and  22 are known.
Given x ~ N, n1 , x1 , n2 , x2 , x1 independent of x2 .
Assume 1 = 22 and let Q  (x1  x2 ) .
E (Q)  E (x1  2 x2 )  1  22  0
var(x1 ) var(x2 )
var(Q)  var(x1  2 x2 )  var(x1 )  var(2 x2 )  var( x1 )  22 var( x2 )  4
n1 n2
Q0 x1  2 x2
Z0  
SD(Q)  12 n1  4  22 n2
And, reject H0 if Z 0  Z /2
4.32.
Nonconformities occur in glass bottles according to a Poisson distribution . A random sample of 100
bottles contains a total of 11 nonconformities.
(a) Develop a procedure for testing the hypothesis that the mean of a Poisson distribution equals a
specified value 0. Hint: Use the normal approximation to the Poisson.
Wish to test H0:  = 0 versus H1:   0.

n
Select random sample of n observations x1, x2, …, xn. Each xi ~ POI(). x
i 1
i ~ POI(n ) .
Using the normal approximation to the Poisson, if n is large, x = x/n = ~ N(, /n).
Z0   x    0 / n . Reject H0:  = 0 if |Z0| > Z/2
(b) Use the results of part (a) to test the hypothesis that the mean occurrence rate of nonconformities
is  = 0.15. Use  = 0.01.
x ~ Poi(), n = 100, x = 11, x = x/N = 11/100 = 0.110

Test H0:  = 0.15 versus H1:   0.15, at  = 0.01. Reject H0 if |Z0| > Z/2.
Z/2 = Z0.005 = 2.5758
Z0   x  0  0 n   0.110  0.15 0.15 100  1.0328
(|Z0| = 1.0328) < 2.5758, so do not reject H0.
4.33.
An inspector counts the surface-finish defects in dishwashers. A random sample of five dishwashers
contains three such defects. Is there reason to conclude that the mean occurrence rate of surface-finish
defects per dishwasher exceeds 0.5? Use the results of part (a) of Exercise 4.32 and assume that  =
0.05.
x ~ Poi(), n = 5, x = 3, x = x/N = 3/5 = 0.6

Test H0:  = 0.5 versus H1: >0.5, at  = 0.05. Reject H0 if Z0>Z.
Z = Z0.05 = 1.645
Z0   x  0  0 n   0.6  0.5 0.5 5  0.3162
(Z0 = 0.3162) < 1.645, so do not reject H0.
4.34.
An in-line tester is used to evaluate the electrical function of printed circuit boards. This machine counts
the number of defects observed on each board. A random sample of 1,000 boards contains a total of
688 defects. Is it reasonable to conclude that the mean occurrence rate of defects is  = 1. Use the
results of part (a) of Exercise 4.26 and assume that  = 0.05.
x ~ Poi(), n = 1000, x = 688, x = x/N = 688/1000 = 0.688

Test H0:  = 1 versus H1:   1, at  = 0.05. Reject H0 if |Z0| > Z.
Z/2 = Z0.025 = 1.96
Z0   x  0  0 n   0.688  1 1 1000  9.8663
(|Z0| = 9.8663) > 1.96, so reject H0.
4.35.
An article in Solid State Technology (May 1987) describes an experiment to determine the effect of C2F6
flow rate on etch uniformity on a silicon wafer used in integrated-circuit manufacturing. Three flow rates
are tested, and the resulting uniformity (in percent) is observed for six test units at each flow rate. The
data are shown in Table 4E.4.
(a) Does C2F6 flow rate affect etch uniformity? Answer this question by using an analysis of variance with
 = 0.05.
MTB > Stat > ANOVA > One-Way
One-way ANOVA: Ex4-35Obs versus Ex4-35Flow
Source DF SS MS F P
Ex4-35Flow 2 3.648 1.824 3.59 0.053
Error 15 7.630 0.509
Total 17 11.278
S = 0.7132 R-Sq = 32.34% R-Sq(adj) = 23.32%
Individual 95% CIs For Mean Based on

Pooled StDev
Level N Mean StDev -----+---------+---------+---------+----
125 6 3.3167 0.7600 (---------*----------)
160 6 4.4167 0.5231 (----------*---------)
200 6 3.9333 0.8214 (----------*---------)
-----+---------+---------+---------+----
3.00 3.60 4.20 4.80
Pooled StDev = 0.7132
(F0.05,2,15 = 3.6823)>(F0 = 3.59), so flow rate does not affect etch uniformity at a significance level
 = 0.05. However, the P-value = 0.053 is just slightly greater than 0.05, so there is some evidence that
gas flow rate affects the etch uniformity.
4.35. continued
(b) Construct a box plot of the etch uniformity data. Use this plot, together with the analysis of variance
results, to determine which gas flow rate would be best in terms of etch uniformity (a small percentage
is best).
Gas flow rate of 125 SCCM gives smallest mean percentage uniformity.
4.35. continued
(c) Plot the residuals versus predicted C2F6 flow. Interpret this plot.
Residuals are satisfactory, with no unusual patterns and approximately equal variance over the range of
fitted values.
(d) Does the normality assumption seem reasonable in this problem?
The normality assumption is reasonable.

4.36.
Compare the mean etch uniformity values at each of the C2F6 flow rates from Exercise 4.33 with a scaled
t distribution. Does this analysis indicate that there are differences in mean etch uniformity at the
different flow rates? Which flows produce different results?
Flow Rate Mean Etch Uniformity

125 3.3%
160 4.4%
200 3.9%
scale factor  MSE n  0.5087 6  0.3
Scaled t Distribution
(125) (200) (160)
3.0 3.3 3.6 3.9 4.2 4.5 4.8
Mean Etch Uniformity

4.36 continued
Or, alternatively approximating with the normal distribution:
MTB > Graph > Probability Distribution Plot > View Single
Distribution Plot
The graphs do not indicate a large difference between the mean etch uniformity of the three different
flow rates. The statistically significant difference between the mean uniformities can be seen by
centering the t distribution between, say, 125 and 200, and noting that 160 would fall beyond the tail of
the curve.
4.37.
An article in the ACI Materials Journal (Vol. 84, 1987, pp. 213–216) describes several experiments
investigating the rodding of concrete to remove entrapped air. A 3-in.-diameter cylinder was used, and
the number of times this rod was used is the design variable. The resulting compressive strength of the
concrete specimen is the response. The data are shown in Table 4E.5.
(a) Is there any difference in compressive strength due to the rodding level? Answer this question by
using the analysis of variance with  = 0.05.
One-way ANOVA: Ex4-37Str versus Ex4-37Rod
Source DF SS MS F P
Ex4-37Rod 3 28633 9544 1.87 0.214
Error 8 40933 5117
Total 11 69567
S = 71.53 R-Sq = 41.16% R-Sq(adj) = 19.09%

Pooled StDev
Level N Mean StDev ----+---------+---------+---------+-----
10 3 1500.0 52.0 (-----------*----------)
15 3 1586.7 77.7 (-----------*-----------)
20 3 1606.7 107.9 (-----------*-----------)
25 3 1500.0 10.0 (-----------*----------)
----+---------+---------+---------+-----
1440 1520 1600 1680
Pooled StDev = 71.5
ANOVA P-value = 0.214, so no difference due to rodding level at  = 0.05.

4.37. continued
(b) Construct box plots of compressive strength by rodding level. Provide a practical interpretation of
these plots.
Boxplot of Ex4-37Str
Level 25 exhibits considerably less variability than the other three levels.
(c) Construct a normal probability plot of the residuals from this experiment. Does the assumption of a
normal distribution for compressive strength seem reasonable?
Normplot of Residuals for Ex4-37Str
The normal distribution assumption for compressive strength is reasonable.

4.38.
Compare the mean compressive strength at each rodding level from Exercise 4.37 with a scaled t
distribution. What conclusions would you draw from this plot?
Rodding Level Mean Compressive Strength

10 1500
15 1587
20 1607
25 1500
scale factor  MSE n  5117 3  41
S c a le d t D is tr ib u t io n
(10 , 25 ) (1 5 ) (2 0 )
1418 1459 1500 1541 1582 1623 1664
M e a n C o m p re s s iv e S tr e n g t h
There is no difference due to rodding level.

4.39.
An aluminum producer manufactures carbon anodes and bakes them in a ring furnace prior to use in the
smelting operation. The baked density of the anode is an important quality characteristic, as it may
affect anode life. One of the process engineers suspects that firing temperature in the ring furnace
affects baked anode density. An experiment was run at four different temperature levels, and six anodes
were baked at each temperature level. The data from the experiment are shown in Table 4E.6.
(a) Does firing temperature in the ring furnace affect mean baked anode density?
One-way ANOVA: Ex4-39Den versus Ex4-39T
Source DF SS MS F P
Ex4-39T 3 0.457 0.152 1.45 0.258
Error 20 2.097 0.105
Total 23 2.553
S = 0.3238 R-Sq = 17.89% R-Sq(adj) = 5.57%
Pooled StDev
Level N Mean StDev --------+---------+---------+---------+-
500 6 41.700 0.141 (----------*----------)
525 6 41.583 0.194 (----------*----------)
550 6 41.450 0.339 (----------*----------)
575 6 41.333 0.497 (----------*----------)
--------+---------+---------+---------+-
41.25 41.50 41.75 42.00
ANOVA P-value = 0.258. At  = 0.05, temperature level does not significantly affect mean baked anode
density.
4.39. continued
(b) Find the residuals for this experiment and plot them on a normal probability scale. Comment on the
plot.
Normality assumption is reasonable.
(c) What firing temperature would you recommend using?
Since statistically there is no evidence to indicate that the means are different, select the temperature
with the smallest variance, 500C (see Boxplot), which probably also incurs the least cost (lowest
temperature).
4.40.
Plot the residuals from Exercise 4.36 against the firing temperatures. Is there any indication that
variability in baked anode density depends on the firing temperature? What firing temperature would
you recommend using?
As firing temperature increases, so does variability. More uniform anodes are produced at lower
temperatures. Recommend 500C for smallest variability.
4.41.
An article in Environmental International (Vol. 18, No. 4, 1992) describes an experiment in which the
amount of radon released in showers was investigated. Radon-enriched water was used in the
experiment, and six different orifice diameters were tested in showerheads. The data from the
experiment are shown in Table 4E.7.
(a) Does the size of the orifice affect the mean percentage of radon released? Use the analysis of
variance and  = 0.05.
One-way ANOVA: Ex4-41Rad versus Ex4-41Dia
Source DF SS MS F P
Ex4-41Dia 5 1133.38 226.68 30.85 0.000
Error 18 132.25 7.35
Total 23 1265.63
S = 2.711 R-Sq = 89.55% R-Sq(adj) = 86.65%

Pooled StDev
Level N Mean StDev ----+---------+---------+---------+-----
0.37 4 82.750 2.062 (---*---)
0.51 4 77.000 2.309 (---*---)
0.71 4 75.000 1.826 (---*---)
1.02 4 71.750 3.304 (----*---)
1.40 4 65.000 3.559 (---*---)
1.99 4 62.750 2.754 (---*---)
----+---------+---------+---------+-----
63.0 70.0 77.0 84.0
Orifice size does affect mean % radon release, at  = 0.05.

4.41.(a) continued
Smallest % radon released at 1.99 and 1.4 orifice diameters.

4.41. continued
(b) Analyze the residuals from this experiment.
Residuals violate the assumption of normally distributed errors.
Variability in residuals does not appear to depend on the magnitude of predicted (or fitted) values.
The assumption of equal variance at each factor level appears to be violated, with larger variances at the
larger diameters (1.02, 1.40, 1.99).
4.42.
An article in the Journal of the Electrochemical Society (Vol. 139, No. 2, 1992, pp. 524–532) describes an
experiment to investigate the low-pressure vapor deposition of polysilicon. The experiment was carried
out in a large-capacity reactor at SEMATECH in Austin, Texas. The reactor has several wafer positions,
and four of these positions are selected at random. The response variable is film thickness uniformity.
Three replicates of the experiment were run, and the data are shown in Table 4E.8.
(a) Is there a difference in the wafer positions? Use the analysis of variance and  = 0.05.
One-way ANOVA: Ex4-42Un versus Ex4-42Pos
Source DF SS MS F P
Ex4-42Pos 3 16.220 5.407 8.29 0.008
Error 8 5.217 0.652
Total 11 21.437
S = 0.8076 R-Sq = 75.66% R-Sq(adj) = 66.53%

Pooled StDev
Level N Mean StDev --------+---------+---------+---------+-
1 3 4.3067 1.4636 (------*------)
2 3 1.7733 0.3853 (------*------)
3 3 1.9267 0.4366 (------*------)
4 3 1.3167 0.3570 (------*------)
--------+---------+---------+---------+-
1.5 3.0 4.5 6.0

4.42.(a) continued
There is a statistically significant difference in wafer position, 1 is different from 2, 3, and 4.
(b) Estimate the variability due to wafer positions.
MSfactor  MSE 5.4066  0.6522

ˆ2    0.3962
n 12
(c) Estimate the random error component.
ˆ 2  MSE  0.6522
ˆuniformity
2
 ˆ2  ˆ 2  0.3962  0.6522  1.0484
4.42. continued
(d) Analyze the residuals from this experiment and comment on model adequacy.
Normality assumption is probably not unreasonable, but there are two very unusual observations – the
outliers at either end of the plot – therefore model adequacy is questionable. Both outlier residuals are
from wafer position 1. The variability in residuals does appear to depend on the magnitude of predicted
(or fitted) values.
4.43.
The tensile strength of a paper product is related to the amount of hardwood in the pulp. Ten samples
are produced in the pilot plant, and the data obtained are shown in Table 4E.9.
(a) Fit a linear regression model relating strength to percentage hardwood.
MTB > Stat > Regression > Regression
Regression Analysis: Ex4-43Str versus Ex4-43Per
The regression equation is

Ex4-43Str = 144 + 1.88 Ex4-43Per
Predictor Coef SE Coef T P

Constant 143.824 2.522 57.04 0.000
Ex4-43Per 1.8786 0.1165 16.12 0.000
S = 2.20320 R-Sq = 97.0% R-Sq(adj) = 96.6%
Analysis of Variance
Source DF SS MS F P
Regression 1 1262.1 1262.1 260.00 0.000
Residual Error 8 38.8 4.9
Total 9 1300.9
(b) Test the model in part (a) for significance of regression.

H0 : 1  0 vs H1 : 1  0
MSR 1262.1 (Equation 4.97)
F0    260.00; F0.05,1,8  5.32  260.00
MSE 4.9
Therefore, the regression is significant.
(c) Find a 95% confidence interval on the parameter 1.

ˆ  t
1  
se ˆ    ˆ  t
 /2,n 2 1 1 1 se ˆ
 /2,n 2  
1
1.8786  2.306  0.1165  1  1.8786  2.306  0.1165 (Equation 4.113)

1.610  1  2.147
4.44.
A plant distills liquid air to produce oxygen, nitrogen, and argon. The percentage of impurity in the
oxygen is thought to be linearly related to the amount of impurities in the air as measured by the
“pollution count” in parts per million (ppm). A sample of plant operating data is shown below:
(a) Fit a linear regression model to the data.
Regression Analysis: Ex4-44Pur versus Ex4-44Poll

Ex4-44Pur = 96.9 - 3.10 Ex4-44Poll

Constant 96.8574 0.4308 224.81 0.000
Ex4-44Poll -3.0955 0.3131 -9.89 0.000
S = 0.457540 R-Sq = 87.5% R-Sq(adj) = 86.6%
Source DF SS MS F P
Regression 1 20.469 20.469 97.78 0.000
Total 15 23.400
The regression model relating purity (y) to pollution count ( x1 ) is given by yˆ  96.9  3.1x1 .
(b) Test for significance of regression.

H0 : 1  0 versus H1 : 1  0
Since the P-value for the F statistic is very small (approximately 0), we reject the null hypothesis and
conclude that the regression model is significant.
(c) Find a 95% confidence interval on 1.

   
ˆ1  t.025,8 se ˆ1  1  ˆ1  t.025,8 se ˆ1
3.19  2.16(0.31)  1  3.19  2.16(0.31)
3.86  1  2.52
4.45.
Plot the residuals from Problem 4.43 and comment on model adequacy.
The assumption of equal variance at each factor level appears to be satisfied. The normality assumption
appears to be satisfied. Variability in residuals does not appear to depend on the magnitude of
predicted (or fitted) values.
4.46.
Plot the residuals from Problem 4.44 and comment on model adequacy.
Based on the residual plots the normality and constant variance assumptions seems to be satisfied.
4.47.
The brake horsepower developed by an automobile engine on a dynamometer is thought to be a
function of the engine speed in revolutions per minute (rpm), the road octane number of the fuel, and
the engine compression. An experiment is run in the laboratory and the data are drawn in Table 4E.10:
(a) Fit a multiple regression model to these data.
Regression Analysis: Ex4-47HP versus Ex4-47RPM, Ex4-47Oct, Ex4-47Com

Ex4-47HP = - 266 + 0.0107 Ex4-47RPM + 3.13 Ex4-47Oct + 1.87 Ex4-47Com

Constant -266.03 92.67 -2.87 0.021
Ex4-47RPM 0.010713 0.004483 2.39 0.044
Ex4-47Oct 3.1348 0.8444 3.71 0.006
Ex4-47Com 1.8674 0.5345 3.49 0.008
S = 8.81239 R-Sq = 80.7% R-Sq(adj) = 73.4%
Source DF SS MS F P
Regression 3 2589.73 863.24 11.12 0.003
Total 11 3211.00
Source DF Seq SS
Ex4-47RPM 1 509.35
Ex4-47Oct 1 1132.56
Ex4-47Com 1 947.83
4.47. continued
(b) Test for significance of regression. What conclusions can you draw?
H0 : 1  2  3  0 vs H1 : at least one  i  0
MSR 863.24
F0    11.12 (Equation 4.97)
MSE 77.66
F0.05,3,8  4.07  11.12
Since the P-value for the F statistic is very small (approximately 0), we reject the null hypothesis and
conclude that at least one of the three variables – rpm ( ), road octane number of the fuel ( ) and the
engine compression ( ) – has a nonzero regression coefficient.
(c) Based on t-tests, do you need all three regressor variables in the model?
The P-values corresponding to the variables rpm, road octane number and compression are 0.044, 0.006
and 0.008, respectively. Since these are all less than a significance level of 0.05, each of the three
variables contributes significantly to the regression model.
4.48.
Analyze the residuals from the regression model in Exercise 4.47. Comment on model adequacy.
Based on the residual plots, there do not seem to be any violations of the necessary assumptions for
multiple linear regression.
4.49. 
Table 4E.11 contains the data from a patient satisfaction survey for a group of 25 randomly selected
patients at a hospital. In addition to satisfaction, data were collected on patient age and an index that
measured the severity of illness.
4.49. continued
(a) Fit a linear regression model relating satisfaction to patient age.
Regression Analysis: Ex4-49Sat versus Ex4-49Age

Ex4-49Sat = 131 - 1.29 Ex4-49Age

Constant 131.096 6.832 19.19 0.000
Ex4-49Age -1.2898 0.1292 -9.98 0.000
S = 9.37523 R-Sq = 81.2% R-Sq(adj) = 80.4%
Source DF SS MS F P
Regression 1 8756.7 8756.7 99.63 0.000
Total 24 10778.2
Unusual Observations
Obs Ex4-49Age Ex4-49Sat Fit SE Fit Residual St Resid
9 27.0 75.00 96.27 3.61 -21.27 -2.46R
21 70.0 59.00 40.81 3.11 18.19 2.06R
R denotes an observation with a large standardized residual.
The regression model relating satisfaction (y) to patient age ( x1 ) is given by yˆ  131  1.29*Age
(b) Test for significance of regression.
H0: β1 = 0 versus H1: β1 ≠ 0

Since the P-value for the F statistic is very small (approximately 0), we reject the null hypothesis at a
significance level of  = 0.05 and conclude that the regression model is significant.
(c) What portion of the total variability is accounted for by the regressor variable age?
81.2% (R2) of the total variability is accounted for by Age.

4.50. 
Analyze the residuals from the regression model on the patient satisfaction data from Exercise 4.49.
Comment on the adequacy of the regression model.
Plot points on a normal probability plot of the residuals tend to fall along a straight line, indicating that
the assumption of normally distributed model errors is valid.
Plots of the residuals versus predicted Satisfaction and Age are relatively uniform over the range of
values and do not indicate any issues with the assumptions of constant variance.
These plots do not reveal any model inadequacy or unusual problem with the assumptions.
4.51. 
Reconsider the patient satisfaction data in Table 4E.11. Fit a multiple regression model using both
patient age and severity as the regressors.
(a) Test for significance of regression.
Regression Analysis: Ex4-49Sat versus Ex4-49Age, Ex4-49Sev

Ex4-49Sat = 143 - 1.03 Ex4-49Age - 0.556 Ex4-49Sev

Constant 143.472 5.955 24.09 0.000
Ex4-49Age -1.0311 0.1156 -8.92 0.000
Ex4-49Sev -0.5560 0.1314 -4.23 0.000
S = 7.11767 R-Sq = 89.7% R-Sq(adj) = 88.7%
Source DF SS MS F P
Regression 2 9663.7 4831.8 95.38 0.000
Total 24 10778.2
Source DF Seq SS
Ex4-49Age 1 8756.7
Ex4-49Sev 1 907.0
Unusual Observations
Obs Ex4-49Age Ex4-49Sat Fit SE Fit Residual St Resid
9 27.0 75.00 92.28 2.90 -17.28 -2.66R
R denotes an observation with a large standardized residual.
The regression model relating satisfaction (y) to patient age and severity of illness is given by
yˆ  143  1.03 Age  0.556  Severity
Test H0: β1 = β2 = 0 versus H1: at least one βi ≠ 0. Since the P-value for the F statistic is very small
(approximately 0), we reject the null hypothesis at a significance level of  = 0.05 and conclude that at
least one of the two variables – has a nonzero regression coefficient.
4.51. continued
(b) Test for the individual contribution of the two regressors. Are both regressor variables needed in the
model?
Test H0: βAge = 0 versus H1: βAge ≠ 0. Since the P-value for the t statistic is very small (0.000), reject the
null hypothesis at a significance level of  = 0.05 and conclude that Age contributes significantly to the
model.
Test H0: βSeverity = 0 versus H1: βSeverity ≠ 0. Since the P-value for the t statistic is very small (0.000), reject
the null hypothesis at a significance level of  = 0.05 and conclude that Severity contributes significantly
to the model.
(c) Has adding severity to the model improved the quality of the model fit? Explain your answer.
Adding Severity to the model has improved measures of model quality, including R2 (increasing R2,
adjusted R2, and R2-prediction) and decreasing MS-Error (from 87.9 to 50.7).
4.52. 
Analyze the residuals from the multiple regression model on the patient satisfaction data from Exercise
4.51. Comment on the adequacy of the regression model.
Plot points on a normal probability plot of the residuals tend to fall along a straight line, indicating that
the assumption of normally distributed model errors is valid.
Plots of the residuals versus predicted Satisfaction, Age and Severity are relatively uniform over the
range of values and do not indicate any issues with the assumptions of constant variance.
These plots do not reveal any model inadequacy or unusual problem with the assumptions.
4.53.
Consider the Minitab output below.
(a) Fill in the missing values. What conclusions would you draw?
31.400  30
Z  4.1667
0.336
P  2Pr  Z  4.1667  0.00003
The small P-value would lead to concluding that the mean is not 30.
(b) Is this a one-sided or two-sided test?
This is a two-sided test (given in the first line of the output). This is why the P-value above was double
the probability instead of just simply the probability.
(c) Use the output and a normal table to find a 95% CI on the mean.
 
x  Z /2    x  Z /2
n n
1.3 1.3
31.4  1.96    31.4  1.96 (Equation 4.29)
15 15
30.7421    32.0579
This answer agrees with the given CI.
(d) How was the SE mean calculated?
1.3
SE mean=  0.336 .
15
(e) What is the P-value if the alternative hypothesis is H1:  > 30?
P-value=0.00003/2=0.000015
4.54.
Suppose that you are testing H0 : 1  2 versus H1 : 1  2 with a n1 = n2 = 15. Use the table of the
t distribution percentage points to find lower and upper bounds on the P-value for the following
observed values of the test statistic:
Degrees of freedom,  = n1 + n2 – 2 = 15 + 15 – 2 = 28
(a) t0 = 2.19
0.01 < P-value < 0.025
(b) t0 = 3.50
0.0005 < P-value < 0.001
(c) t0 = 2.88
0.0025 < P-value < 0.005
(d) t0 = 1.42
0.05 < P-value < 0.10
4.55.
Suppose that you are testing H0 : 1  2 versus H1 : 1  2 with a n1 = n2 = 10. Use the table of the
t distribution percentage points of find lower and upper bounds on the P-value of the following
observed values of the test statistic:
Degrees of freedom,  = n1 + n2 – 2 = 10 + 10 – 2 = 18
(a) t0  2.48
t (18) Prob
2.101 0.025
2.48 p-val
2.552 0.01
Since this is a two-sided test, we double the probabilities. 0.02 < P-value < 0.05.
(b) t0  2.41 Notice that we can find the probabilities associated with the absolute value of the test
statistic, since the t distribution is symmetric about 0.
t (18) Prob
2.101 0.025
2.48 p-val
2.552 0.01
(c) t0  2.98
t (18) Prob
2.878 0.005
2.98 p-val
3.197 0.0025
(d) t0  1.89
t (18) Prob
1.734 0.05
1.89 p-val
2.101 0.025
4.56.
(a) Fill in the missing values. Can the null hypothesis be rejected at the 0.05 level? Why?
94.58  95
StDev=3.00; T   0.626 . Since the P-value is greater than 0.05, the null hypothesis cannot
0.671
be rejected at the 0.05 level.
Since the hypotheses are mu=95 vs not =95, this is a two-sided test.
(c) How many degrees of freedom are there on the t-test statistic?
Since N=20, there are N-1=19 df.
(d) Use the output and a normal table to find a 95% CI on the mean.
A 95% CI on the mean is given by (93.176, 95.984).
(e) Suppose that the hypotheses had been H0 :   90 versus H1 :   90 . What conclusions would you
have drawn?
94.58  90
T  6.83 with a corresponding P-value of approximately 0. Thus for this set of hypotheses
0.671
we would reject the null hypothesis and conclude that the mean is greater than 90.
4.57.
(a) Is this a one-sided or two-sided test?
This is a two-sided test (given in the first line of the output).
(b) Can the null hypothesis be rejected at the 0.05 level?
Since the given P-value of 0.313 is larger than 0.05, we cannot reject the null hypothesis at this level.
(c) Construct an approximate 90% CI for p.
pˆ 1  pˆ  pˆ 1  pˆ 
pˆ  Z /2  p  pˆ  Z /2
n n
0.3267 1  0.3267  0.3267  1  0.3267
0.3267  1.645  p  0.3267  1.645 (Equation 4.44)
300 300
0.2822  p  0.3712
(d) What is the P-value if the alternative hypothesis is H1: p > 0.3?
The P-value is half the P-value for the two sided alternative, so P = 0.131/2 = 0.156.
4.58.
(a) Fill in the missing values.
Estimate for difference=50.2-51.98= -1.78; DF=N1+N2-2=28.
(b) Can the null hypothesis be rejected at the 0.05 level? Why?
Since the P-value=0.019 is less than 0.05, the null hypothesis can be rejected at the 0.05 level.
(c) Use the output and the t-table to find a 99% CI on the difference in means.
A 99% CI on the difference in means is given by
1 1 1 1
x1  x2  t0.005,28 sp   1  2  x1  x2  t0.005,28 sp 
n1 n2 n1 n2
1 1 1 1
50.2  51.98  2.763(1.9602)   1  2  50.2  51.98  2.763(1.9602) 
15 15 15 15
3.76  1  2  0.198
(d) Suppose that the alternative hypothesis was H1: 1 = 2 versus H1: 1 > 2. What is the P-value? What
conclusions would you draw?
50.2  51.98
T-Value =  2.49 ,
1 1
1.9602 
15 15
P-value = P(T>-2.49 with 28 df) = 0.99. Since the P-value is larger than 0.05, we fail to reject the null
hypothesis. There is insufficient evidence to show that 1  2 .
4.59.
(a) Fill in the missing values.

N2=301/0.602=500; Estimate for difference=185/300-301/500=0.0146667;
Z:
x  x 185  301
pˆ  1 2   0.6075
n1  n2 300  500
pˆ1  pˆ2 0.616667  0.602
Z   0.411 .
1 1  1 1 
pˆ 1  pˆ     0.6075(1  0.6075)   
 n1 n2   300 500 

Since the hypotheses are difference = 0 (vs not =0), this is a two-sided test.
(c) What is the P-value if the alternative hypothesis is H1: p1 = p2 versus H0: p1 > p2?
P-value = 0.68/2=0.34.
(d) Construct an approximate 90% CI for the difference in the two proportions.
A 90% CI for the difference in the two proportions is given by
pˆ1 1  pˆ1  pˆ2 1  pˆ2  pˆ1 1  pˆ1  pˆ2 1  pˆ2 
pˆ1  pˆ2  Z /2   p1  p2  pˆ1  pˆ2  Z /2 
n1 n2 n1 n2
0.616667(1  0.616667) 0.602(1  0.602)
0.616667  0.602  1.645   p1  p2
300 500
0.616667(1  0.616667) 0.602(1  0.602)
 0.616667  0.602  1.645 
300 500
0.0439  p1  p2  0.0732
4.60.
Consider a one-way or single-factor ANOVA with four treatments and five replications. Use the table of
the F distribution percentage points to find lower and upper bounds on the P-value for the following
observed values of the test statistic.
ν1 = a − 1 = 4 – 1 = 3, ν2 = a (n – 1) = 4 (5 – 1) = 16
 0.25 0.10 0.05 0.025 0.01

F, 3, 16 1.51 2.46 3.24 4.08 5.29
(a) F0 = 7.50
P-value < 0.01
(b) F0 = 4.25
0.01 < P-value < 0.025
(c) F0 = 6.28
P-value < 0.01
(d) F0 = 1.70
0.10 < P-value < 0.25
4.61.
Consider the Minitab ANOVA output below. Fill in the blanks. You may give bounds on the P-value.
What conclusions can you draw based on the information in this display?
MSFactor = SSFactor/3 = 18.30

DF Error = DF Total – DF Factor = 12
MSError = SSError/12 = 1.6475
F = MSFactor/MSError = 11.11
P-value < 0.01
Since the P-value is smaller than 0.01, there is strong evidence against the null hypothesis. We conclude
that the means are not the same for all factor levels, and that changing the level of the factor will
significantly affect the response.

ch04 PDF

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

ch04 PDF

Uploaded by

Copyright:

Available Formats

Chapter 4

Inferences About Process Quality

IMPORTANT TERMS AND CONCEPTS

Confidence intervals on means, unknown Sampling distribution

From Appendix II, (Z0) = (2.75) = 0.99702

From Appendix II, (Z0) = (1.86) = 0.96856

From Appendix II, (Z0) = (|−2.05|) = (2.05) = 0.97982

Same answer as for (b)

From Appendix II, (Z0) = (2.60) = 0.99534

From Appendix II, (Z0) = (1.85) = 0.96784

From Appendix II, (Z0) = (2.15) = 0.98422

From Appendix II, (Z0) = (3.72) = 0.99990

From Appendix II, (Z0) = (2.35) = 0.99061

From Appendix II, (Z0) = (1.99) = 0.97670

From Appendix II, (Z0) = (2.18) = 0.98537

From Appendix II, (Z0) = (1.85) = 0.96784

From Appendix IV and ν = n – 1 = 10 – 1 =9,

From Appendix IV and ν = 9,

From Appendix IV and ν = 9,

Same answer as for (b)

From Appendix IV and ν = n – 1 = 12 – 1 = 11,

From Appendix IV and ν = 11,

From Appendix IV and ν = 11,

From Appendix IV and ν = 11,

From Appendix IV and ν = n – 1 = 20 – 1 = 19,

From Appendix IV and ν = 19,

From Appendix IV and ν = 19,

From Appendix IV and ν = 19,

Since  is known, use the standard normal distribution:

(b) Find the P-value for this test.

Construct a 95% two-sided confidence interval on mean bearing diameter.

The assumed standard deviation = 0.002

N Mean SE Mean 95% CI

(b) What is the P-value for this test?

P-value = 1  (Z0) = 1  (2.828) = 1  0.99766 = 0.00234

(c) Discuss why a one-sided alternative was chosen in part (a).

Test of mu = 125 vs > 125

t, n1 = t0.05, 101 = 1.833 (from Appendix IV)

MTB > Stat > Basic Statistics > 1-Sample t

MTB > Stat > Basic Statistics > 1-Sample t

Variable N Mean StDev SE Mean 90% CI T P

Probability Plot of Ex 4-9

MTB > Stat > Basic Statistics > 1-Sample t

Test of mu = 13.4 vs not = 13.4

Variable N Mean StDev SE Mean 95% CI T P

Test of mu = 13.4 vs not = 13.4

Variable N Mean StDev SE Mean 99% CI T P

Probability Plot of Ex 4-11

x ~ N(, ), 0 = 12,  = 0.01

MTB > Stat > Basic Statistics > 1-Sample t

4.12. (b) continued

MTB > Stat > Basic Statistics > 1-Sample t

Variable N Mean StDev SE Mean 99% CI T P

Probability Plot of Ex 4-12

x ~ N(, ), 0 = 0.5025,  = 0.05

MTB > Stat > Basic Statistics > 1-Sample Z

Test of mu = 0.5025 vs not = 0.5025

N Mean SE Mean 95% CI Z P

(b) Find the P-value for this test.

P-value = 2[1  (Z0)] = 2[1  (|−17.89|)] = 2[1  1] = 0

x ~ N(, ), n = 16, x = 10.259 V, s = 0.999 V, 0 = 12,  = 0.05

MTB > Stat > Basic Statistics > 1-Sample t

Variable N Mean StDev SE Mean 95% CI T P