Logistic Regression: A Self-learning Text, Third Edition (Statistics in the Health Sciences)

Objectives Upon completing this chapter, the learner should be able to:

1. Given a logistic model for a study situation involving a
   single exposure variable and several control variables,
   compute or recognize the expression for the odds ratio
   for the effect of exposure on disease status that adjusts
   for the confounding and interaction effects of functions
   of control variables:
   a. When the exposure variable is dichotomous and
   coded (a, b) for any two numbersaandb
   b. When the exposure variable is ordinal and two
   exposure values are specified
   c. When the exposure variable is continuous and two
   exposure values are specified


2. Given a study situation involving a single nominal
   exposure variable with more than two (i.e.,
   polytomous) categories, state or recognize a logistic
   model that allows for the assessment of the
   exposure–disease relationship controlling for potential
   confounding and assuming no interaction.


3. Given a study situation involving a single nominal
   exposure variable with more than two categories,
   compute or recognize the expression for the odds ratio
   that compares two categories of exposure status,
   controlling for the confounding effects of control
   variables and assuming no interaction.


4. Given a study situation involving several distinct
   exposure variables, state or recognize a logistic model
   that allows for the assessment of the joint effects of the
   exposure variables on disease controlling for the
   confounding effects of control variables and assuming
   no interaction.


5. Given a study situation involving several distinct
   exposure variables, state or recognize a logistic model
   that allows for the assessment of the joint effects of
   the exposure variables on disease controlling for the
   confounding and interaction effects of control
   variables.

Objectives 75