Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

Get Started for Free

pbkrtest

Parametric Bootstrap, Kenward-Roger and Satterthwaite Based Methods for Test in Mixed Models

Test in mixed effects models. Attention is on mixed effects models as implemented in the 'lme4' package. For linear mixed models, this package implements (1) a parametric bootstrap test, (2) a Kenward-Roger-typ modification of F-tests for linear mixed effects models and (3) a Satterthwaite-type modification of F-tests for linear mixed effects models. The package also implements a parametric bootstrap test for generalized linear mixed models. The facilities of the package are documented in the paper by Halehoh and Højsgaard, (2012, <doi:10.18637/jss.v059.i09>). Please see 'citation("pbkrtest")' for citation details.

Functions (16)

compute_auxillary

Compute_auxillary quantities needed for the Satterthwaite approximation.

Sugar beets data

data-budworm

budworm data

Compute Deviance of an LMM as a Function of Variance Parameters

get_Fstat_ddf

Compute denominator df for F-test

get_covbeta

Compute cov(beta) as a function of varpar of an LMM

Adjusted denomintor degress freedom for linear estimate for linear mixed model.

Extract (or "get") components from a KRmodcomp object.

Internal functions for the pbkrtest package

internal-pbkrtest

pbkrtest internal

F-test and degrees of freedom based on Kenward-Roger approximation

Ajusted covariance matrix for linear mixed models according to Kenward and Roger

model-coerce

Conversion between a model object and a restriction matrix

Model comparison using parametric bootstrap methods.

Calculate reference distribution using parametric bootstrap

sat-modcomp

F-test and degrees of freedom based on Satterthwaite approximation

pbkrtest

Parametric Bootstrap, Kenward-Roger and Satterthwaite Based Methods for Test in Mixed Models

v0.5.1

GPL (>= 2)

Authors

Ulrich Halekoh [aut, cph], Søren Højsgaard [aut, cre, cph]

Initial release

We don't support your browser anymore

Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.