Essentials of Biostatistics in Public Health, Third Edition

Lisa M. Sullivan
End-of-Chapter Answers

CHAPTER 6

2. A clinical trial is planned to compare an experimental medication designed to lower

blood pressure to a placebo. Before starting the trial, a pilot study is conducted involving

10 participants. The objective of the study is to assess how systolic blood pressure

changes over time untreated. Systolic blood pressures are measured at baseline and again

4 weeks later. Compute a 95% CI for the difference in blood pressures over 4 weeks.

Answer:

Baseline: 120 145 130 160 152 143 126 121 115 135

4 Weeks: 122 142 135 158 155 140 130 120 124 130

Baseline 4 Weeks Difference = 4 Weeks – Baseline Difference2

120 122 2 4
145 142 –3 9
130 135 5 25
160 158 –2 4
152 155 3 9
143 140 –3 9
126 130 4 16
121 120 –1 1
115 124 9 81
135 130 –5 25
9 183
ΣDifferenc e 9
Xd    0.9
n 10

ΣDifferenc es 2  (ΣΣDiffere ces) 2 /n 183  (9) 2 /10

s   19.43  4.4
n 1 9

sd
Xd  t , df = n – 1 = 10 – 1 = 9
n

Copyright © 2018 by Jones & Bartlett Learning, LLC, an Ascend Learning Company 1
Essentials of Biostatistics in Public Health, Third Edition
Lisa M. Sullivan
End-of-Chapter Answers

For 95% confidence, t = 2.262

sd
Xd  t
n

4.4
0.9  (2.262)
10

0.9 ± 3.1

(–2.2, 4.0)

3. The main trial is conducted and involves a total of 200 patients. Patients are enrolled and

randomized to receive either the experimental medication or the placebo. The data shown

here are data collected at the end of the study after 6 weeks on the assigned treatment.

Experimental Placebo
(n = 100) (n = 100)
Mean (SD) systolic blood pressure 120.2 (15.4) 131.4 (18.9)
% Hypertensive 14% 22%
% With side effects 6% 8%

a. Generate a 95% CI for the difference in mean systolic blood pressures between groups.

Answer:

1 1
(X1 - X 2 )  ZSp 
n1 n 2

Check s12/s22 = 15.42/18.92 = 0.66

(n 1  1)s 12  (n 2  1)s 22
Sp 
n1  n 2  2

(100  1)15.4 2  (100 - 1)18.9 2

Sp 
100  100  2

Copyright © 2018 by Jones & Bartlett Learning, LLC, an Ascend Learning Company 2
Essentials of Biostatistics in Public Health, Third Edition
Lisa M. Sullivan
End-of-Chapter Answers

Sp  297.19 =17.2

1 1
(120.2 - 131.4)  1.960(17.2)  .
100 100

–11.2 ± 4.77

(–16.0, –6.4)

b. Generate a 95% CI for the difference in proportions of patients with hypertension

between groups.

Answer:

p̂1 (1 - p̂1 ) p̂ 2 (1  p̂ 2 )
(p̂1 - p̂ 2 )  Z 
n1 n2

Sample size is adequate with at least five successes and failures in each group.

0.14(1  0.14) 0.22(1  0.22)

(0.14  0.22)  1.96 
100 100

–0.08 ± 1.96 (0.054)

–0.08 ± 0.106

(–0.19, 0.03)

c. Generate a point estimate for the RR of side effects in patients assigned to the

experimental group as compared to placebo. Generate a 95% CI for the RR.

Answer:

R̂R = p̂ 1/ p̂ 2 = 0.06/0.08 = 0.75

(n 1 - x 1 )/x 1 (n 2 - x 2 )/x 2
Ln( R̂R)  Z 
n1 n2

Sample size is adequate with at least five successes and failures in each group.

Copyright © 2018 by Jones & Bartlett Learning, LLC, an Ascend Learning Company 3
Essentials of Biostatistics in Public Health, Third Edition
Lisa M. Sullivan
End-of-Chapter Answers

94/6 92/8
Ln(0.75)  1.96 
100 100

–0.29 ± 1.96 (0.521)

–0.29 ± 1.02

(–1.31, 0.73)

The 95% CI for Ln(RR) is (–1.31, 0.73). To generate the CI for the RR, we take the

antilog (exp) of the lower and upper limits:

(exp(–1.31), exp(0.73))

(0.27, 2.08)

4. The following data are collected as part of a study of coffee consumption among

undergraduate students. The following values reflect cups per day consumed:

3 4 6 8 2 1 0 2

a. Compute the sample mean.

Answer:

X X2

3 9
4 16

6 36

8 64

2 4

1 1

0 0

2 4

Copyright © 2018 by Jones & Bartlett Learning, LLC, an Ascend Learning Company 4
Essentials of Biostatistics in Public Health, Third Edition
Lisa M. Sullivan
End-of-Chapter Answers

26 134
ΣX 26
X   3.3
n 8

b. Compute the sample standard deviation.

Answer:

ΣX 2  (ΣΣ 2 )/n 134  (26) 2 /8 134  84.5

s    7.07  2.7
n 1 7 7

c. Construct a 95% CI for the mean number of cups of coffee consumed among all

undergraduates.

Answer:

s
Xt , df = n – 1 = 8 – 1 = 7
n

For 95% confidence, t = 2.365

s
Xt
n

2.7
3.3  (2.365)
8

3.3 ± 2.26

(1.0, 5.6)

5. A clinical trial is conducted comparing a new pain medication for arthritis. Participants

are randomly assigned to receive the new medication or a placebo. The outcome is pain

relief within 30 minutes; the data are shown here.

Pain Relief No Pain Relief

Copyright © 2018 by Jones & Bartlett Learning, LLC, an Ascend Learning Company 5
Essentials of Biostatistics in Public Health, Third Edition
Lisa M. Sullivan
End-of-Chapter Answers

New medication 44 76
Placebo 21 99

p̂ 1 = 44/120 = 0.367, p̂ 2 = 21/120 = 0.175

a. Estimate the RD in pain relief between treatments.

Answer:

R̂D = p̂ 1 – p̂ 2 = 0.367 – 0.175 = 0.192

b. Estimate the RR in pain relief between treatments.

Answer:

R̂R = p̂ 1/ p̂ 2 = 0.367/0.175 = 2.097

c. Estimate the OR in pain relief between treatments.

Answer:

p̂1 /(1  p̂1 ) 0.367 / 0.633 0.580

ÔR =   = 2.74
p̂ 2 /(1  p̂ 2 ) 0.175 / 0.825 0.212

d. Construct a 95% CI for the OR.

Answer:

1 1 1 1
Ln( ÔR)  Z   
x 1 (n 1  x 1 ) x 2 (n 2  x 2 )

Sample size is adequate with at least five successes and failures in each group.

1 1 1 1
Ln(2.74)  1.96   
44 76 21 99

1.01 ± 1.96 (0.306)

1.01 ± 0.60

Copyright © 2018 by Jones & Bartlett Learning, LLC, an Ascend Learning Company 6
Essentials of Biostatistics in Public Health, Third Edition
Lisa M. Sullivan
End-of-Chapter Answers

(0.41, 1.61)

The 95% CI for Ln(OR) is (0.41, 1.61). To generate the CI for the odds ratio, we take the

antilog (exp) of the lower and upper limits:

(exp(0.41), exp(1.61))

(1.51, 5.00)

10. Suppose in the study described in Problem 9, each participant is also asked if the assigned

medication causes any stomach upset. Among the 50 participants, 12 report stomach

upset with the experimental medication. Construct a 90% CI for the proportion of

participants who might experience stomach upset with the experimental medication.

Answer:

p̂ = 12/50 = 0.24

p̂(1 - p̂)
p̂  Z
n

Sample size is adequate with at least five successes and failures in the sample.

0.24(1 - 0.24)
0.24  1.645
50

0.24 ± 0.099

(0.14, 0.34)

16. A clinical trial is run comparing a new drug for high cholesterol to a placebo. A total of

40 participants are randomized (with equal assignment to treatments) to receive either the

new drug or placebo. Their total serum cholesterol levels are measured after 8 weeks on

the assigned treatment. Participants receiving the new drug reported a mean total serum

Copyright © 2018 by Jones & Bartlett Learning, LLC, an Ascend Learning Company 7
Essentials of Biostatistics in Public Health, Third Edition
Lisa M. Sullivan
End-of-Chapter Answers

cholesterol level of 209.5 (SD = 21.6) and participants receiving the placebo reported a

mean total serum cholesterol level of 228.1 (SD = 19.7).

a. Construct a 95% CI for the difference in mean total serum cholesterol levels between

participants receiving the new drug versus placebo.

Answer:

1 1
(X1 - X 2 )  tSp 
n1 n 2

df = n1 + n2 –2 = 20 + 20 –2 = 38

Check s12/s22 =21.62/19.72 = 1.20

(n 1  1)s 12  (n 2  1)s 22
Sp 
n1  n 2  2

(20  1)21.6 2  (20 - 1)19.7 2

Sp   427.33  20.7
20  20  2

1 1
(209.5 - 228.1)  2.024(20.7) 
20 20

–18.6 ± 13.25

(–31.85, –5.35)

b. Is the new drug effective? Justify briefly.

Answer:

Yes. The 95% CI for the difference in means does not include the null value (0), and

thus there is a statistically significant difference in mean total serum cholesterol levels

between participants receiving the new drug versus placebo.

Copyright © 2018 by Jones & Bartlett Learning, LLC, an Ascend Learning Company 8