Exercises 2197.14 Compas and others (1994) were surprised to find that young children under stress actually
report fewer symptoms of anxiety and depression than we would expect. But they also no-
ticed that their scores on a Lie scale (a measure of the tendency to give socially desirable
answers) were higher than expected. The population mean for the Lie scale on the Chil-
dren’s Manifest Anxiety Scale (Reynolds and Richmond, 1978) is known to be 3.87. For a
sample of 36 children under stress, Compas et al. found a sample mean of 4.39, with a stan-
dard deviation of 2.61.
a. How would we test whether this group shows an increased tendency to give socially ac-
ceptable answers?
b. What would the null hypothesis and research hypothesis be?
c. What can you conclude from the data?
7.15 Calculate the 95% confidence limits for m for the data in Exercise 7.14. Are these limits
consistent with your conclusion in Exercise 7.14?
7.16 Hoaglin, Mosteller, and Tukey (1983) present data on blood levels of beta-endorphin as a
function of stress. They took beta-endorphin levels for 19 patients 12 hours before surgery,
and again 10 minutes before surgery. The data are presented below, in fmol/ml:
ID 12345678910
12 hours 10.0 6.5 8.0 12.0 5.0 11.5 5.0 3.5 7.5 5.8
10 minutes 6.5 14.0 13.5 18.0 14.5 9.0 18.0 42.0 7.5 6.0
ID 11 12 13 14 15 16 17 18 19
12 hours 4.7 8.0 7.0 17.0 8.8 17.0 15.0 4.4 2.0
10 minutes 25.0 12.0 52.0 20.0 16.0 15.0 11.5 2.5 2.0
Based on these data, what effect does increased stress have on endorphin levels?
7.17 Why would you use a matched-sample ttest in Exercise 7.16?
7.18 Construct 95% confidence limits on the true mean difference between endorphin levels at
the two times described in Exercise 7.16.
7.19 Hout, Duncan, and Sobel (1987) reported on the relative sexual satisfaction of married cou-
ples. They asked each member of 91 married couples to rate the degree to which they agreed
with “Sex is fun for me and my partner” on a four-point scale ranging from “never or occa-
sionally” to “almost always.” The data appear below (I know it’s a lot of data, but it’s an
interesting question):
Husband111111111111111
Wife 111111122222223
Husband111122222222222
Wife 344411222222223
Husband222222222333333
Wife 334444444122222
Husband333333333333344
Wife 333344444444411
Husband444444444444444
Wife 222222223333333
Husband4444444444444444
Wife 3344444444444444
Start out by running a matched-sample ttest on these data. Why is a matched-sample test
appropriate?
7.20 In the study referred to in Exercise 7.19, what, if anything does your answer to that question
tell us about whether couples are sexually compatible? What do we know from this analy-
sis, and what don’t we know?