- Which of the following isnota property of the logistic
model? (Circle one choice.)
a. The model form can be written as
P(X)=1/{1þexp[(aþ~biXi)]}, where “exp{}”
denotes the quantity e raised to the power of the
expression inside the brackets.
b. logit P(X)¼aþ~biXiis an alternative way to
state the model.
c. ROR¼exp[~bi(X 1 iX 0 i)] is a general expression
for the odds ratio that compares two groups of
Xvariables.
d. ROR¼P{exp[bi(X 1 iX 0 i)]} is a general expression
for the odds ratio that compares two groups of
Xvariables.
e. For any variableXi, ROR¼exp[bi], wherebiis the
coefficient ofXi, gives an adjusted odds ratio for
the effect ofXi.
Suppose a logistic model involving the variables D¼HPT
[hypertension status (0, 1)],X 1 ¼AGE(continuous),X 2 ¼
SMK(0, 1),X 3 ¼SEX(0, 1),X 4 ¼CHOL (cholesterol level,
continuous), andX 5 ¼OCC[occupation (0, 1)] is fit to a set
of data. Suppose further that the estimated coefficients of
each of the variables in the model are given by the
following table:
VARIABLE COEFFICIENT
CONSTANT 4.3200
AGE 0.0274
SMK 0.5859
SEX 1.1523
CHOL 0.0087
OCC 0.5309- State the form of the logistic model that was fit to
these data (i.e., state the model in terms of the
unknown population parameters and the
independent variables being considered). - State the form of theestimatedlogistic model obtained
from fitting the model to the data set. - State the estimated logistic model in logit form.
- Assuming the study design used was a follow-up
design, compute the estimated risk for a 40-year-old
male (SEX¼1) smoker (SMK¼1) with CHOL¼ 200
and OCC¼1. (You need a calculator to answer this
question.)
36 1. Introduction to Logistic Regression