modelAvg: Model Averaging for Linear Mixed Models

In cAIC4: Conditional Akaike Information Criterion for 'lme4' and 'nlme'

Description

Function to perform model averaging for linear mixed models based on the weight selection criterion as proposed by Zhang et al. (2014).

Usage

modelAvg(models, opt = TRUE)

Arguments

models	A list object containing all considered candidate models fitted by lmer of the lme4-package or of class lme.
opt	logical. If TRUE (the default) the model averaging approach based on Zhang et al. is applied. If FALSE the underlying weights are calculated as smoothed weights as proposed by Buckland et al. (1997).

Value

An object containing the function calls of the underlying candidate models, the values of the model averaged fixed effects, the values of the model averaged random effects, the results of the weight optimization process, as well as a list of the candidate models themselves.

Author(s)

Benjamin Saefken & Rene-Marcel Kruse

References

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

Zhang, X., Zou, G., & Liang, H. (2014). Model averaging and weight choice in linear mixed-effects models. Biometrika, 101(1), 205-218.

See Also

lme4-package, lmer

Examples

data(Orthodont, package = "nlme")
models <- list(
    model1 <- lmer(formula = distance ~ age + Sex + (1 | Subject) + age:Sex,
               data = Orthodont),
    model2 <- lmer(formula = distance ~ age + Sex + (1 | Subject),
               data = Orthodont),
    model3 <- lmer(formula = distance ~ age + (1 | Subject),
                 data = Orthodont),
    model4 <- lmer(formula = distance ~ Sex + (1 | Subject),
                data = Orthodont))
foo <- modelAvg(models = models)
foo

cAIC4 documentation built on Sept. 22, 2021, 5:07 p.m.