Extends the approach proposed by Firth (1993) for bias reduction of MLEs in exponential family models to the multinomial logistic regression model with general covariate types. Modification of the logistic regression score function to remove first-order bias is equivalent to penalizing the likelihood by the Jeffreys prior, and yields penalized maximum likelihood estimates (PLEs) that always exist. Hypothesis testing is conducted via likelihood ratio statistics. Profile confidence intervals (CI) are constructed for the PLEs.

Author | Sarah Colby <colby@lunenfeld.ca>, Sophia Lee, Juan Pablo Lewinger, Shelley Bull <bull@lunenfeld.ca> |

Date of publication | 2010-04-02 17:08:39 |

Maintainer | Sarah Colby <colby@lunenfeld.ca> |

License | GPL (>= 2) |

Version | 1.0 |

pmlr

pmlr/data

pmlr/data/enzymes.R

pmlr/data/hepatitis.R

pmlr/DESCRIPTION

pmlr/man

pmlr/man/enzymes.Rd
pmlr/man/hepatitis.Rd
pmlr/man/pmlr.Rd
pmlr/NAMESPACE

pmlr/R

pmlr/R/getA.R
pmlr/R/getAstar.R
pmlr/R/getMLEs.R
pmlr/R/getPLEs.R
pmlr/R/getV.R
pmlr/R/getW.R
pmlr/R/misc.R
pmlr/R/pmlr.R
pmlr/R/profile.R
pmlr/R/profileCIs.R
pmlr/R/SASalgo.R
pmlr/R/summary.pmlr.R
pmlr/R/test.LR.R
pmlr/R/test.wald.R
Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.