Multinomial logit bias reduction via the Poisson log-linear model

Abstract

For the parameters of a multinomial logistic regression, it is shown how to obtain the bias-reducing penalized maximum likelihood estimator by using the equivalent Poisson log-linear model. The calculation needed is not simply an application of the Jeffreys prior penalty to the Poisson model. The development allows a simple and computationally efficient implementation of the reduced-bias estimator, using standard software for generalized linear models.