2.1 Mean P 0.1 10.

Atkins Wei
4.8 STDEV DOF 39 adults used the
1.685 weight loss pro
40 n found to be 2.1
0.82127 Lower limit 90% confidenc
3.3787 Upper limit
subjects. Does
appear to be pr
We are 90% confident that the true mean weight loss for all subjects who use the Atkins weight
loss program falls between 0.821 and 3.378.

A weight loss of 2.1 lb or more per month is considered practical and sustainable for most people.
Since the lower bound of the confidence interval (0.37 lb) is below the practical significance threshold of
2.1 lb per month, we may conclude that the Atkins program may not be practical for most people in the
long term.

Confidence interval suggests that the program appears to be effective, as the mean weight loss of 2.1 lb is
significantly different from zero
10. Atkins Weight Loss Program In a test of weight loss programs, 40
adults used the Atkins
weight loss program. After 12 months, their mean weight loss was
found to be 2.1 lb, with a stan-dard deviation of 4.8 lb. Construct a
90% confidence interval estimate of the mean weight loss for all such
subjects. Does the Atkins program appear to be effective? Does it
appear to be practical?
 0.4 MEAN P 0.02 12. Garlic for Reducing Cholest
21.0 STDEV DOF 48 cholesterol, 49 subjects were tre
2.40658 and after the treatment. The chan
49 n (in mg>dL) had a mean of 0.4 an
7.61974 Upper limit Raw Garlic vs Commercial Garl
-6.81974 Lowerlimit
Moderate Hypercholesterolemia
Construct a 98% confidence inte
the garlic treatment. What does t
in reducing LDL cholesterol?

This means that we are 98% confident that the true mean net change in LDL cholesterol
levels after the garlic treatment falls between -6.81 and 7.61 mg/dL.

Confidence interval includes zero means that we cannot rule out the possibility that the
true effect of garlic treatment on LDL cholesterol levels is zero or negligible.
 lic for Reducing Cholesterol In a test of the effectiveness of garlic for lowering
erol, 49 subjects were treated with raw garlic. Cholesterol levels were measured before
er the treatment. The changes (before minus after) in their levels of LDL cholesterol
>dL) had a mean of 0.4 and a standard deviation of 21.0 (based on data from “Effect of
arlic vs Commercial Garlic Supplements on Plasma Lipid Concentrations in Adults with
ate Hypercholesterolemia,” by Gardner et al., Archives of Internal Medicine, Vol. 167).
uct a 98% confidence interval estimate of the mean net change in LDL cholesterol after
ic treatment. What does the confidence interval suggest about the effectiveness of garlic
cing LDL cholesterol?
 5 27.3 MEAN P 0.01 16. Los Angeles Commute Time R
25 18.56 STDEV DOF 31 commute times:
45 2.744 5 25 45 5 5 40 25 8 50 5 5 30 15
5 32 n 25 45 75 60 40 25 8 50 10 10 30 1
5 18.30844 Lower limit
40 36.31656 Upper limit
25 The data do not appear to be from a normally distributed population.
8 We are 99% confident that the true population mean lies within this interval.
50
5
5
30
15
25
50
18
25
45
75
60
40
25
8
50
10
10
30
15
25
50
20
30
s Angeles Commute Time Repeat the preceding exercise using these 32 Los Angeles
ute times:
5 5 5 40 25 8 50 5 5 30 15 25 50 18
75 60 40 25 8 50 10 10 30 15 25 50 20 30

al.
 Yes No Total
Male 138 724 862
Female 228 913 1141
Total 366 1637 2003

Expected Values
Yes No
Male 157.5097 704.4903
Female 208.4903 932.5097

X-squared (X^2) distribution

X^2 5.191
DOF 1
Confidence level 0.01 0.05
Table A4 6.635 3.841
Fail to reject the Reject the null
null hypothesis of hypothesis at the
independence at 0.05 significance
0.01 significance level
level
6. Ghosts The following table summarizes results from a Pew Research Center survey in
which subjects were asked whether they had seen or been in the presence of a ghost. Use a 0.01
significance level to test the claim that gender is independent of response. Does the conclusion
change if the significance level is changed to 0.05?
Yes No
Male 138 724
Female 228 913
 Correct Wrong Total 8. Accuracy of Fingerprint Identifications An expe
Novice 331 113 444 accuracy of fingerprint experts to the accuracy of
Fingerprint Expertise,” by Tangen, Thompson, and
Expert 409 35 444 No. 8). The data in the table are based on trials in
Total 740 148 888 fingerprints. Use a 0.05 significance level to deter
pendent of whether the evaluator is an expert or
Correct Wrong
Expected Values Novice 331 113
Correct Wrong Expert 409 35
Novice 370 74
Expert 370 74

X-squared (X^2) distribution

Degrees of Freedom
1

X^2 49.330
DOF 1
Confidence 0.05
Table A4 3.841
Reject the null hypothesis at the 0.05 significance level
erprint Identifications An experiment was conducted to compare the
rint experts to the accuracy of novices (based on data from “Identifying
se,” by Tangen, Thompson, and McCarthy, Psychological Science, Vol. 22,
the table are based on trials in which the evaluators were given matching
0.05 significance level to determine whether correct identification is inde-
r the evaluator is an expert or a novice.
Arkansas California Texas 12. Arsenic in Rice Listed below are am
4.8 1.5 5.6 different states. The amounts are in m
ing size. The data are from the Food an
4.9 3.7 5.8 test the claim that the three samples a
5 4 6.6 amounts of arsenic appear to be differ
5.4 4.5 6.9 arsenic in the samples from Texas have
from Texas poses the greatest health p
5.4 4.9 6.9 Arkansas 4.8 4.9 5.0 5.4 5.4 5.4 5.6 5.6
5.4 5.1 6.9 California 1.5 3.7 4.0 4.5 4.9 5.1 5.3 5.4
5.6 5.3 7.1 Texas 5.6 5.8 6.6 6.9 6.9 6.9 7.1 7.3 7.5
5.6 5.4 7.3
5.6 5.4 7.5
5.9 5.5 7.6
6 5.6 7.7
6.1 5.6 7.7 P value <0.0001. Reject

We cannot conclude that brown rice fro

Anova: Single Factor

SUMMARY
Groups Count Sum
Arkansas 12 65.7
California 12 56.5
Texas 12 83.6

ANOVA
Source of Variation SS df
Between Groups 31.651666667 2
Within Groups 22.758333333 33

Total 54.41 35
nic in Rice Listed below are amounts of arsenic in samples of brown rice from three
states. The amounts are in micrograms of arsenic and all samples have the same serv-
The data are from the Food and Drug Administration. Use a 0.05 significance level to
claim that the three samples are from populations with the same mean. Do the
of arsenic appear to be different in the different states? Given that the amounts of
n the samples from Texas have the highest mean, can we conclude that brown rice
as poses the greatest health problem?
s 4.8 4.9 5.0 5.4 5.4 5.4 5.6 5.6 5.6 5.9 6.0 6.1
a 1.5 3.7 4.0 4.5 4.9 5.1 5.3 5.4 5.4 5.5 5.6 5.6
6 5.8 6.6 6.9 6.9 6.9 7.1 7.3 7.5 7.6 7.7 7.7

0.0001. Reject

t conclude that brown rice from Texas poses the greatest health problem based solely on the fact
the highest mean amount of arsenic.

Average Variance
5.475 0.1747727273
4.7083333333 1.4153787879
6.9666666667 0.4787878788

MS F P-value F crit
15.825833333 22.947748078 5.677E-07 3.284917651
0.6896464646