Model selection criteria in beta regression with varying dispersion

TL;DR

This paper introduces two new model selection criteria for beta regressions with varying dispersion, improving accuracy and computational efficiency over traditional joint selection methods.

Contribution

The paper proposes novel criteria and a two-step selection scheme specifically designed for beta regressions with varying dispersion, addressing limitations of joint covariate selection.

Findings

Joint selection is less accurate in finite samples.

The new criteria outperform traditional methods in simulations.

The two-step scheme reduces computational cost.

Abstract

We address the issue of model selection in beta regressions with varying dispersion. The model consists of two submodels, namely: for the mean and for the dispersion. Our focus is on the selection of the covariates for each submodel. Our Monte Carlo evidence reveals that the joint selection of covariates for the two submodels is not accurate in finite samples. We introduce two new model selection criteria that explicitly account for varying dispersion and propose a fast two step model selection scheme which is considerably more accurate and is computationally less costly than usual joint model selection. Monte Carlo evidence is presented and discussed. We also present the results of an empirical application.