brglm2 (0.1.3)

Bias Reduction in Generalized Linear Models.

http://cran.r-project.org/web/packages/brglm2

Estimation and inference from generalized linear models based on various methods for bias reduction. The brglmFit fitting method can achieve reduction of estimation bias either through the adjusted score equations approach in Firth (1993) and Kosmidis and Firth (2009) , or through the direct subtraction of an estimate of the bias of the maximum likelihood estimator from the maximum likelihood estimates as in Cordeiro and McCullagh (1991) . In the special case of generalized linear models for binomial and multinomial responses, the adjusted score equations approach returns estimates with improved frequentist properties, that are also always finite, even in cases where the maximum likelihood estimates are infinite (e.g. complete and quasi-complete separation). Estimation in all cases takes place via a quasi Fisher scoring algorithm, and S3 methods for the construction of of confidence intervals for the reduced-bias estimates are provided.

Maintainer: Ioannis Kosmidis
Author(s): Ioannis Kosmidis [aut, cre]

License: GPL-2 | GPL-3

Uses: enrichwith, MASS, Matrix, nnet, testthat, knitr, rmarkdown
Reverse suggests: WeightIt

Released over 2 years ago.