d¼average di¤erence
¼
31
12
¼ 2 :58 mmHg
sd^2 ¼
185 ð 31 Þ^2 = 12
11
¼ 9 : 54
sd¼ 3 : 09
SEðdÞ¼
3 : 09
ffiffiffiffiffi
12
p
¼ 0 : 89
t¼
2 : 58
0 : 89
¼ 2 : 90
Using the column corresponding to the upper tail area of 0.05 in Appendix C,
we have a tabulated value of 1.796 for 11 df. Since
t¼ 2 : 90 > 2 : 201
we conclude that the null hypothesis of no blood pressure change should be
rejected at the 0.05 level; there is enough evidence to support the hypothesis of
increasedsystolic blood pressure (one-sided alternative).
Example 7.4 Data in epidemiologic studies are sometimes self-reported.
Screening data from the hypertension detection and follow-up program in
Minneapolis, Minnesota (1973–1974) provided an opportunity to evaluate the
accuracy of self-reported height and weight. Table 7.3 gives the percent dis-
crepancy between self-reported and measured height:
x¼
self-reported heightmeasured height
measured height
100%
TABLE 7.3
Men Women
Education n Mean SD n Mean SD
aHigh school 476 1.38 1.53 323 0.66 1.53
bCollege 192 1.04 1.31 62 0.41 1.46
252 COMPARISON OF POPULATION MEANS