UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Multinomial logit bias reduction via the Poisson log-linear model

Kosmidis, I; Firth, D; (2011) Multinomial logit bias reduction via the Poisson log-linear model. BIOMETRIKA , 98 (3) 755 - 759. 10.1093/biomet/asr026.

Full text not available from this repository.

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.

Type:Article
Title:Multinomial logit bias reduction via the Poisson log-linear model
DOI:10.1093/biomet/asr026
Keywords:Jeffreys prior, Leverage, Logistic linear regression, Poisson trick, LOGISTIC-REGRESSION, MAXIMUM-LIKELIHOOD
UCL classification:UCL > School of BEAMS > Faculty of Maths and Physical Sciences > Statistical Science

Archive Staff Only: edit this record