lava.tobit: Estimation and simulation of probit and tobit latent variable...
In kkholst/lava.tobit: Latent Variable Models with Censored and Binary Outcomes

Framwork for estimating parameters and simulate data from Latent Variable Models with binary and censored observations. Plugin for the lava package

Package:	lava.tobit
Type:	Package
Version:	0.4-5
Date:	2012-03-15
License:	GPL-3
LazyLoad:	yes

Klaus K. Holst Maintainer: <kkho@biostat.ku.dk>

library('lava.tobit')
m <- lvm(list(c(y,z) ~ x, y~z))
## Simulate 200 observation from path analysis model
## with all slopes and residual variances set to 1 and intercepts 0:
d <- sim(m,200,seed=1)
## Dichotomize y and introduce censoring on z
d <- transform(d, y=as.factor(y>0), z=Surv(z,z<2))

##  if (requireNamespace("mets",quietly=TRUE)) {
##    e <- estimate(m,d,control=list(trace=1),estimator="gaussian")
##    effects(e,y~x)
##  }