R: Conditional Akaike Information Criterion for 'lme4' and...

cAIC4-package {cAIC4}

R Documentation

Conditional Akaike Information Criterion for 'lme4' and 'nlme'

Description

Provides functions for the estimation of the conditional Akaike information in generalized mixed-effect models fitted with (g)lmer() from 'lme4', lme() from 'nlme' and gamm() from 'mgcv'. For a manual on how to use 'cAIC4', see Saefken et al. (2021) <doi:10.18637/jss.v099.i08>.

Details

The DESCRIPTION file:

Package:	cAIC4
Type:	Package
Title:	Conditional Akaike Information Criterion for 'lme4' and 'nlme'
Version:	1.0
Date:	2021-09-22
Author:	Benjamin Saefken, David Ruegamer, Philipp Baumann and Rene-Marcel Kruse, with contributions from Sonja Greven and Thomas Kneib
Maintainer:	David Ruegamer <david.ruegamer@gmail.com>
Depends:	lme4(>= 1.1-6), methods, Matrix, stats4, nlme
Imports:	RLRsim, mgcv, mvtnorm
Suggests:	gamm4
Description:	Provides functions for the estimation of the conditional Akaike information in generalized mixed-effect models fitted with (g)lmer() from 'lme4', lme() from 'nlme' and gamm() from 'mgcv'. For a manual on how to use 'cAIC4', see Saefken et al. (2021) <doi:10.18637/jss.v099.i08>.
License:	GPL (>= 2)
Packaged:	2021-09-22 12:34:56 UTC; david
NeedsCompilation:	no
Date/Publication:	2014-08-12 11:48:10
RoxygenNote:	7.1.1

Index of help topics:

Zambia                  Subset of the Zambia data set on childhood
                        malnutrition
anocAIC                 Comparison of several lmer objects via cAIC
cAIC                    Conditional Akaike Information for 'lme4' and
                        'lme'
cAIC4-package           Conditional Akaike Information Criterion for
                        'lme4' and 'nlme'
deleteZeroComponents    Delete random effect terms with zero variance
getWeights              Optimize weights for model averaging.
getcondLL               Function to calculate the conditional
                        log-likelihood
guWahbaData             Data from Gu and Wahba (1991)
modelAvg                Model Averaging for Linear Mixed Models
predictMA               Prediction of model averaged linear mixed
                        models
print.cAIC              Print method for cAIC
stepcAIC                Function to stepwise select the (generalized)
                        linear mixed model fitted via (g)lmer() or
                        (generalized) additive (mixed) model fitted via
                        gamm4() with the smallest cAIC.
summaryMA               Summary of model averaged linear mixed models

Author(s)

Benjamin Saefken, David Ruegamer, Philipp Baumann and Rene-Marcel Kruse, with contributions from Sonja Greven and Thomas Kneib

Maintainer: David Ruegamer <david.ruegamer@gmail.com>

References

Saefken, B., Kneib T., van Waveren C.-S. and Greven, S. (2014) A unifying approach to the estimation of the conditional Akaike information in generalized linear mixed models. Electronic Journal Statistics Vol. 8, 201-225.

Greven, S. and Kneib T. (2010) On the behaviour of marginal and conditional AIC in linear mixed models. Biometrika 97(4), 773-789.

Efron , B. (2004) The estimation of prediction error. J. Amer. Statist. Ass. 99(467), 619-632.

Examples

b <- lmer(Reaction ~ Days + (Days | Subject), sleepstudy)

cAIC(b)