Conditional probabilities and item information given specified latent process values for lcmm or multlcmm object with ordinal outcomes.

The function computes the conditional probability and information function of each level of each ordinal outcome and the information function at the item level. Confidence bands (and median) can be computed by a Monte Carlo approximation.

Usage

ItemInfo(
  x,
  lprocess,
  condRE_Y = FALSE,
  nsim = 200,
  draws = FALSE,
  ndraws = 2000,
  ...
)

Arguments

x

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

lprocess

numeric vector containing the latent process values at which the predictions should be computed.

condRE_Y

for multlcmm objects only, logical indicating if the predictions are conditional to the outcome-specific random-effects or not. Default to FALSE= the predictions are marginal to these random effects.

nsim

number of points used in the numerical integration (Monte-Carlo) with splines or Beta link functions. nsim should be relatively important (nsim=200 by default).

draws

optional boolean specifying whether median and confidence bands of the predicted values should be computed (TRUE). A Monte Carlo approximation of the posterior distribution of the predicted values is computed and the median, 2.5% and 97.5% percentiles are given. Otherwise, the predicted values are computed at the point estimate. By default, draws=FALSE.

ndraws

if draws=TRUE, ndraws specifies the number of draws that should be generated to approximate the posterior distribution of the predicted values. By default, ndraws=2000.

...

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

Value

An object of class ItemInfo with values :

- ItemInfo: If draws=FALSE, returns a matrix with 3 columns: the first column indicates the name of the outcome, the second indicates the latent process value and the last is the computed Fisher information. If draws=TRUE, returns a matrix with 5 columns: the name of the outcome, the latent process value and the 50%, 2.5% and 97.5% percentiles of the approximated posterior distribution of information.

- LevelInfo: If draws=FALSE, returns a matrix with 5 columns: the first column indicates the name of the outcome, the second indicates the outcome's level, the third indicates the latent process value and the two last contain the probability and Fisher information. If draws=TRUE, returns a matrix with 5 columns: the name of the outcome, the outcome's level, the latent process value and the 50%, 2.5% and 97.5% percentiles of the approximated posterior distribution of the probability and information.

- object: the model from which the computations are done.

- IC: indicator specifying if confidence intervals are computed.

Author

Cecile Proust-Lima, Viviane Philipps

Examples

# \dontrun{
## This is a toy example to illustrate the information functions.
## The binary outcomes are arbitrarily created, please do not
## consider them as relevent indicators.
data_lcmm$Yord1 <- as.numeric(data_lcmm$Ydep1>10)
data_lcmm$Yord2 <- as.numeric(data_lcmm$Ydep2>25)
m <- multlcmm(Yord1+Yord2~Time+I(Time^2),random=~Time,subject='ID',ng=1,
data=data_lcmm,link="thresholds")
info <- ItemInfo(m,lprocess=seq(-4,4,length.out=100),draws=TRUE)
plot(info)

par(mfrow=c(1,2))
plot(info, which="LevelInfo", outcome="Yord1")
plot(info, which="LevelInfo", outcome="Yord2")

plot(info, which="LevelProb", outcome="Yord1")
plot(info, which="LevelProb", outcome="Yord2")

# }