A Picture's Worth a Thousand Words: Visualizing n-dimensional Overlap in Logistic Regression Models with Empirical Likelihood

TL;DR

This paper introduces a geometric and empirical likelihood-based approach to visualize and assess the overlap in multidimensional logistic regression models, providing new tools and rules for higher-dimensional analysis.

Contribution

It translates the overlap condition into an empirical likelihood framework and offers R code for visualizing and analyzing overlap in multidimensional predictor models.

Findings

Empirical likelihood maximization characterizes overlap geometrically.

R code effectively visualizes overlap in dimensions less than four.

Rules for generating minimal higher-dimensional overlap structures are provided.

Abstract

In this note, conditions for the existence and uniqueness of the maximum likelihood estimate for multidimensional predictor, binary response models are introduced from a sensitivity testing point of view. The well known condition of Silvapulle is translated to be an empirical likelihood maximization which, with existing R code, mechanizes the process of assessing overlap status. The translation shifts the meaning of overlap, defined by geometrical properties of the two-predictor groups, from the intersection of their convex cones is non-empty to the more understandable requirement that the convex hull of their differences contains zero. The code is applied to reveal the character of overlap by examining minimal overlapping structures and cataloging them in dimensions fewer than four. Rules to generate minimal higher dimensional structures which account for overlap are provided. Supplementary materials are available online.