Determining the Relative Importance of Predictors in Logistic Regression: An Extension of Relative Weight Analysis

Download pdf
Abstract/Description: Techniques such as dominance analysis and relative weights analysis recently have been proposed in order to evaluate more accurately predictor importance in ordinary least squares regression. Similar questions of predictor importance also arise in instances when logistic regression is the primary mode of analysis. This paper presents an extension of relative weights analysis that can be applied in logistic regression and thus aids in the determination of predictor importance. We briefly review relative importance techniques and then discuss a new procedure for calculating relative importance estimates in logistic regression. Finally, we present a substantive example applying this new approach to an example data set.
Subject(s): dominance analaysis -- logistic regression -- relative importance -- relative weight analysis