deviance.em.glm

object

An n-by-p design matrix.

A vector of observation of length n.

A n length vector of observation weight terms. This is currently designed to be either the exposure for a Poisson model or the number of trials for a Logistic model.

weight

Model deviance (calculated from deviance residuals)

Implementation of Expectation Maximization (EM) regression of general linear models.
The package currently supports Poisson and Logistic regression with variable weights, with underlying theory included in the vignettes.
New users are recommended to look at the em.glm() and small.em() functions - the outputs of which are supported by AIC(), BIC(), and logLik() calls.
Several plot functions have been included for useful diagnostics and model exploration.
Methods are based on the theory of Dempster et al (1977, ISBN:00359246), and follow the methods of Hastie et al. (2009) <doi:10.1007/978-0-387-21606-5_7> and A.
Zeileis et al (2017) <doi:10.18637/jss.v027.i08>.

deviance.em.glm: Model deviance (calculated from deviance residuals)

Description

Usage

Arguments

Value