An Additional Measure of Overall Effect Size for Logistic Regression Models

作者：Allen Jeff^*; Le Huy

来源：Journal of Educational and Behavioral Statistics, 2008, 33(4): 416-441.

DOI：10.3102/1076998607306081

• logistic regression
• overall effect size
• overall odds ratio
• R-squared

Users of logistic regression models often need to describe the overall predictive strength, or effect size, of the model's predictors. Analogs of R 2 have been developed, but none of these measures are interpretable on the same scale as effects of individual predictors. Furthermore, R 2 analogs are not invariant to the base rate (overall proportion of successes), making it difficult to compare effect sizes across data sets. The authors propose a measure of overall effect size that is interpretable on the same scale as effects of individual predictors and is invariant to the base rate. They explore the properties of the overall odds ratio and illustrate its use through an example. The), also provide interpretive guidance and illustrate how statistical software can be used to compute the proposed measure.

• 出版日期2008-12