Boosting with copula-based components

TL;DR

This paper introduces copula-based additive models for binary outcomes that effectively capture complex interactions without discretising continuous variables, offering improved or comparable predictive performance.

Contribution

It presents a novel copula-based additive modeling approach for binary data, including an efficient fitting algorithm and model selection procedures, implemented in an R package.

Findings

Predictive performance is better or comparable to existing methods.

Models effectively capture complex interaction effects.

No discretisation of continuous covariates needed.

Abstract

The authors propose new additive models for binary outcomes, where the components are copula-based regression models (Noh et al, 2013), and designed such that the model may capture potentially complex interaction effects. The models do not require discretisation of continuous covariates, and are therefore suitable for problems with many such covariates. A fitting algorithm, and efficient procedures for model selection and evaluation of the components are described. Software is provided in the R-package copulaboost. Simulations and illustrations on data sets indicate that the method's predictive performance is either better than or comparable to the other methods.