three control variables. Then the logit form
of a model that describes this situation is
given by logit P(X)¼aþbEþg 1 AGEþg 2 SBP
þg 3 CHLþd 1 AGE SBPþd 2 AGE CHL
þd 3 SBPCHL.
T F 12. Given a logistic model of the form logit P(X)¼
aþbEþg 1 AGEþg 2 SBPþg 3 CHL, whereEis
a (0, 1) exposure variable, the odds ratio for the
effect ofEadjusted for the confounding of AGE,
CHL, and SBP is given by exp(b).
T F 13. If a logistic model contains interaction terms
expressible as products of the formEWjwhere
Wjare potential effect modifiers, then the value
of the odds ratio for theE, Drelationship will be
different, depending on the values specified for
theWjvariables.
T F 14. Given the model logit P(X)¼aþbEþg 1 SMK
þg 2 SBP, whereEand SMK are (0, 1) variables,
and SBP is continuous, then the odds ratio for
estimating the effect of SMK on the disease,
controlling forEand SBP is given by exp(g 1 ).
T F 15. GivenE, C 1 , andC 2 , and lettingV 1 ¼C 1 ¼W 1
and V 2 ¼C 2 ¼W 2 , then the corresponding
logistic model is given by logit P(X)¼aþbE
þg 1 C 1 þg 2 C 2 þE(d 1 C 1 þd 2 C 2 ).
T F 16. For the model in Exercise 15, ifC 1 ¼20 and
C 2 ¼5, then the odds ratio for theE, Drelation-
ship has the form exp(bþ 20 d 1 þ 5 d 2 ).68 2. Important Special Cases of the Logistic Model