Efficient MCMC for Binomial Logit Models

This article deals with binomial logit models where the parameters are estimated within a Bayesian framework. Such models arise, for instance, when repeated measurements are available for identical covariate patterns. To perform MCMC sampling, we rewrite the binomial logit model as an augmented model which involves some latent variables called random utilities. It is straightforward, but inefficient, to use the individual random utility model representation based on the binary observations reconstructed from each binomial observation. Alternatively, we present in this article a new method to aggregate the random utilities for each binomial observation. Based on this aggregated representation, we have implemented an independence Metropolis-Hastings sampler, an auxiliary mixture sampler, and a novel hybrid auxiliary mixture sampler. A comparative study on five binomial datasets shows that the new aggregation method leads to a superior sampler in terms of efficiency compared to previously published data augmentation samplers.