Bayesian multinomial regression with class-specific predictor selection

TL;DR

This paper introduces a Bayesian multinomial regression model that allows for class-specific predictor selection, enabling different predictors to influence each class's membership, which enhances model flexibility and interpretability.

Contribution

It proposes a novel Bayesian approach for class-specific predictor selection in multinomial regression, extending traditional models by allowing predictor effects to vary across classes.

Findings

Demonstrates the model's ability to identify relevant predictors for each class.

Shows improved interpretability over traditional methods.

Provides computational advantages in model selection.

Abstract

Consider a multinomial regression model where the response, which indicates a unit's membership in one of several possible unordered classes, is associated with a set of predictor variables. Such models typically involve a matrix of regression coefficients, with the $(j,k)$ element of this matrix modulating the effect of the $k$th predictor on the propensity of the unit to belong to the $j$th class. Thus, a supposition that only a subset of the available predictors are associated with the response corresponds to some of the columns of the coefficient matrix being zero. Under the Bayesian paradigm, the subset of predictors which are associated with the response can be treated as an unknown parameter, leading to typical Bayesian model selection and model averaging procedures. As an alternative, we investigate model selection and averaging, whereby a subset of individual elements of the coefficient matrix are zero. That is, the subset of predictors associated with the propensity to belong to a class varies with the class. We refer to this as class-specific predictor selection. We argue that such a scheme can be attractive on both conceptual and computational grounds.