Skip to contents

The function computes the predicted values of the random effects given observed data provided in input. With multiple latent classes, these predictions are averaged over classes using the posterior class-membership probabilities.

Usage

predictRE(model, newdata, subject = NULL, classpredRE = FALSE)

Arguments

model

an object inheriting from class hlme, lcmm, Jointlcmm or multlcmm representing a general latent class mixed model.

newdata

data frame containing the data from which predictions are to be computed. The data frame should include at least all the covariates listed in model$Xnames2, the marker(s) values and the grouping structure. Names should match exactly the names of the variables in the model.

subject

character specifying the name of the grouping structure. If NULL (the default), the same as in the model will be used.

classpredRE

logical indicating if class specific random effects should be returned. By default, classpredRE is FALSE, so that the random effects are aggregated over the classes.

Value

a data frame containing the grouping structure and the predicted random-effects.

Author

Sasha Cuau, Viviane Philipps, Cecile Proust-Lima

Examples

if (FALSE) { # \dontrun{
library(NormPsy)
paquid$normMMSE <- normMMSE(paquid$MMSE)
paquid$age65 <- (paquid$age - 65)/10
m2b <- hlme(normMMSE ~ age65+I(age65^2)+CEP, random =~ age65+I(age65^2), subject = 'ID',
data = paquid, ng = 2, mixture =~ age65+I(age65^2), B = c(0, 60, 40, 0, -4, 0, -10, 10,
212.869397, -216.421323,456.229910, 55.713775, -145.715516, 59.351000, 10.072221))
predictRE(m2b,newdata=paquid[1:6,])
} # }