getWeights {cAIC4}R Documentation

Optimize weights for model averaging.


Function to constructed an optimal vector of weights for model averaging of Linear Mixed Models based on the proposal of Zhang et al. (2014) of using Stein's Formular to derive a suitable criterion based on the conditional Akaike Information Criterion as proposed by Greven and Kneib. The underlying optimization used is a customized version of the Augmented Lagrangian Method.





An list object containing all considered candidate models fitted by lmer of the lme4-package or of class lme.


An updated object containing a vector of weights for the underlying candidate models, value of the object given said weights as well as the time needed.


For models called via gamm4 or gamm no weight determination via this function is currently possible.


Benjamin Saefken & Rene-Marcel Kruse


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.

Nocedal, J., & Wright, S. (2006). Numerical optimization. Springer Science & Business Media.

See Also

lme4-package, lmer, getME


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 <- getWeights(models = models)

[Package cAIC4 version 0.9 Index]