a. Give an expression for the odds ratio that compares
a person who has SSU¼5 to a person who has
SSU¼0, controlling for AGE and SEX.
b. Give an expression for the odds ratio that compares
a person who has SSU¼1 to a person who has
SSU¼0, controlling for AGE and SEX.
c. Give an expression for the odds ratio that compares
a person who has SSU¼2 to a person who has
SSU¼1, controlling for AGE and SEX.
d. Assuming that the same data set is used for parts b
and c, what is the relationship between the odds
ratios computed in parts b and c?
- Suppose the variable SSU in Question 3 is partitioned
into three categories denoted aslow, medium, andhigh.
a. Revise the model of Question 3 to give the logit
form of a logistic model that treats SSU as a nomi-
nal variable with three categories (assume
no interaction).
b. Using your model of part a, give an expression for
the odds ratio that compares high to low SSU per-
sons, controlling for AGE and SEX.
c. Revise your model of part a to allow for effect
modification of SSU with AGE and with SEX.
d. Revise your odds ratio of part b to correspond to
your model of part c.
- Given the following model
logit P(X)¼aþb 1 NSþb 2 OCþb 3 AFSþg 1 AGEþ
g 2 RACE,
where NS denotes number of sex partners in one’s
lifetime, OC denotes oral contraceptive use (yes/no),
and AFS denotes age at first sexual intercourse
experience,answer the following questions about the
above model:
a. Give an expression for the odds ratio that compares
a person who has NS¼5, OC¼1, and AFS¼26 to
a person who has NS¼5, OC¼1, and AFS¼16,
controlling for AGE and RACE.
b. Give an expression for the odds ratio that compares
a person who has NS¼200, OC¼1, and AFS¼ 26
to a person who has NS¼5, OC¼1, and
AFS¼16, controlling for AGE and RACE.
Test 99
