Comparison of Bias Correction Methods for the Rare Event Logistic Regression

Abstract

We analyzed binary landslide data from the Boeun area with logistic regression. Since the number of landslide occurrences is only 9 out of 5000 observations, this can be regarded as a rare event data. The main issue of logistic regression with the rare event data is a serious bias problem in regression coefficient estimates. Two bias correction methods were proposed before and we quantitatively compared them via simulation. Firth (1993)'s approach outperformed and provided the most stable results for analyzing the rare-event binary data.

Predictive and explanatory models might miss informative features in educational data

“…In general, other studies have tended to find that Firth penalization does outperform logistic regression in the case of outcome imbalance (Heinze and Schemper, 2002;van Smeden et al, 2016;Kim et al, 2014;Doerken et al, 2019) and Log-F penalization shows promise when working with imbalanced data and can outperform Firth-penalization (Ogundimu, 2019;Rahman and Sultana, 2017).…”