Class-specific marginal or subject-specific predictions in the latent process scale for lcmm, Jointlcmm and multlcmm objects

This function provides a matrix containing the class-specific predicted trajectories computed in the latent process scale, that is the latent process underlying the curvilinear outcome(s), for a profile of covariates specified by the user. This function applies only to lcmm, multlcmm and Jointlcmm objects. The function predictY provides the class-specific predicted trajectories computed in the natural scale of the outcome(s).

Usage

predictL(
  x,
  newdata,
  var.time,
  na.action = 1,
  confint = FALSE,
  predRE = NULL,
  ...
)

Arguments

x

an object inheriting from class lcmm,multlcmm or Jointlcmm representing a (joint) (latent class) mixed model involving a latent process and estimated link function(s).

newdata

data frame containing the data from which predictions are computed. The data frame should include at least all the covariates listed in x$Xnames2. Names in the data frame should be exactly x$Xnames2 that are the names of covariates specified in lcmm or multlcmm calls.

var.time

A character string containing the name of the variable that corresponds to time in the data frame (x axis in the plot).

na.action

Integer indicating how NAs are managed. The default is 1 for 'na.omit'. The alternative is 2 for 'na.fail'. Other options such as 'na.pass' or 'na.exclude' are not implemented in the current version.

confint

logical indicating if confidence should be provided. Default to FALSE.

predRE

optional data frame containing the predicted random effects in each latent class. If NULL (the default), marginal prediction are computed.If predRE is specified, subject-specific predictions are computed.

...

further arguments to be passed to or from other methods. They are ignored in this function.

Value

An object of class predictL with values :

- pred : a matrix containing the class-specific predicted values in the latent process scale, the lower and the upper limits of the confidence intervals (if calculated).

- times : the var.time variable from newdata

See also

predictY,predictRE,predictYcond

Author

Cecile Proust-Lima, Viviane Philipps

Examples

#### Prediction from a 2-class model with a Splines link function
if (FALSE) { # \dontrun{
## fitted model
m<-lcmm(Ydep2~Time*X1,mixture=~Time,random=~Time,classmb=~X2+X3,
subject='ID',ng=2,data=data_lcmm,link="splines",B=c(
-0.175,      -0.191,       0.654,      -0.443, 
-0.345,      -1.780,       0.913,       0.016, 
 0.389,       0.028,       0.083,      -7.349, 
 0.722,       0.770,       1.376,       1.653, 
 1.640,       1.285))
summary(m)
## predictions for times from 0 to 5 for X1=0
newdata<-data.frame(Time=seq(0,5,length=100),
X1=rep(0,100),X2=rep(0,100),X3=rep(0,100))
predictL(m,newdata,var.time="Time")
## predictions for times from 0 to 5 for X1=1
newdata$X1 <- 1
predictY(m,newdata,var.time="Time")
} # }