Some issues in logistic regression

Abstract

Much research has been performed in the area of multiple linear regression, with the resuit that the field is well-developed. This is not true of logistic regression, however. The latter presents special problems because the response is not continuous. Some of these problems are: the difficulty of developing a suitable R² statistic, possibly poor results produced by the method of maximum likelihood, and the challenge to develop suitable graphical techniques. We describe recent work in some of these directions, and discuss the need for additional research.

Keywords:

• binary logistic regression
• exact logistic regression
• maximum likelihood
• R²statistics
• correct classification rate (CCR): graphical methods