Skip to main content

Paper No. 10-18

Download 10-18

I Kosmidis and D Firth

Multinomial logit bias reduction via Poisson log-linear model

Date: September 2010

Abstract: It is shown how to obtain the bias-reducing penalized maximum likelihood estimator for the parameters of a multinomial logistic regression by using the equivalent Poisson log-linear model. This allows a simple and computationally efficient implementation of the reduced-bias estimator, using standard software for generalized linear models.

Keywords: Jeffreys prior; leverage; logistic linear regression; Poisson trick.