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. Explain briefly what is meant by goodness of fit.


2. Define “perfect prediction.”


3. Distinguish between “events–trials” format and
   “subject-specific” format for a dataset.


4. Define and illustrate the covariate patterns for a
   specific logistic model.


5. State or recognize the distinction between a fully
   parameterized and a saturated binary logistic model.


6. Given a specific binary logistic model, state or
   recognize the deviance formula for the model.


7. Explain briefly why the deviance statistic is not used for
   assessing goodness of fit when fitting a binary logistic
   regression model.


8. Given a printout of the results of a binary logistic
   regression:
   a. State or recognize the Hosmer–Lemeshow statistic
   b. Carry out a test of hypothesis for goodness of fit
   using the Hosmer–Lemeshow statistic

Objectives 303