pAIC: Pseudo Akaike Information Criterion

In mcglm: Multivariate Covariance Generalized Linear Models

Pseudo Akaike Information Criterion

Description

Computes the pseudo Akaike information criterion (pAIC) for fitted multivariate covariance generalized linear models. The pAIC is defined as

pAIC = -2 \, \ell_p + 2 \, \text{df},

where \ell_p is the pseudo log-likelihood and \text{df} denotes the effective number of parameters in the model.

This criterion is intended for model comparison within the class of mcglm models fitted to the same data.

Usage

pAIC(object, verbose = TRUE)

Arguments

object	An object of class mcglm or a list of such objects. When a list is provided, the pseudo log-likelihood is computed for each model.
verbose	Logical indicating whether the pAIC value should be printed to the console. Defaults to TRUE.

Details

The pAIC is based on the pseudo log-likelihood returned by plogLik and should be used with caution, as it does not correspond to a true likelihood-based information criterion. Comparisons are meaningful only for models fitted to the same response data.

Value

An (invisible) named list with a single element:

pAIC

A numeric value giving the pseudo Akaike information criterion associated with the fitted model(s).

Author(s)

Wagner Hugo Bonat, [e-mail]

Source

Bonat, W. H. (2018). Multiple Response Variables Regression Models in R: The mcglm Package. Journal of Statistical Software, 84(4), 1–30.

See Also

gof, plogLik, ESS, pKLIC, GOSHO, RJC

mcglm documentation built on Jan. 9, 2026, 1:07 a.m.