group, which is 74.5 mmHg. What are the null hypothesis and alterna-
tive hypothesis for this test?5.3 E. canisinfection is a tick-borne disease of dogs that is sometimes con-
tracted by humans. Among infected humans, the distribution of white
blood cell counts has an unknown meanmand a standard deviations.In
the general population the mean white blood count is 7250 per mm^3 .It
is believed that persons infected withE. canismust on average have a
lower white blood cell count. What is the null hypothesis for the test? Is
this a one- or two-sided alternative?
5.4 It is feared that the smoking rate in young females has increased in the
last several years. In 1985, 38% of the females in the 17- to 24-year age
group were smokers. An experiment is to be conducted to gain evidence
to support the increase contention. Set up the appropriate null and
alternative hypotheses. Explain in a practical sense what, if anything, has
occurred if a type I or type II error has been committed.
5.5 A group of investigators wishes to explore the relationship between the
use of hair dyes and the development of breast cancer in females. A
group of 1000 beauticians 40–49 years of age is identified and followed
for five years. After five years, 20 new cases of breast cancer have
occurred. Assume that breast cancer incidence over this time period for
average American women in this age group is 7/1000. We wish to test
the hypothesis that using hair dyes increases the risk of breast cancer. Is
a one- or two-sided test appropriate here? Compute thepvalue for your
choice.
5.6 Height and weight are often used in epidemiological studies as possible
predictors of disease outcomes. If the people in the study are assessed in
a clinic, heights and weights are usually measured directly. However, if
the people are interviewed at home or by mail, a person’s self-reported
height and weight are often used instead. Suppose that we conduct a
study on 10 people to test the comparability of these two methods. Data
from these 10 people were obtained using both methods on each person.
What is the criterion for the comparison? What is the null hypothesis?
Should a two- or a one-sided test be used here?
5.7 Suppose that 28 cancer deaths are noted among workers exposed to
asbestos in a building materials plant from 1981 to 1985. Only 20.5 can-
cer deaths are expected from statewide mortality rates. Suppose that we
want to know if there is a significant excess of cancer deaths among these
workers. What is the null hypothesis? Is a one- or two-sided test appro-
priate here?
5.8 A food frequency questionnaire was mailed to 20 subjects to assess the
intake of various food groups. The sample standard deviation of vitamin
C intake over the 20 subjects was 15 (exclusive of vitamin C supple-
EXERCISES 205