SmoothHazard: Fitting illness-death model for interval-censored data
SmoothHazard is a package for fitting illness-death (and survival)
model with possibly interval-censored data for transition toward transient
state. Left-truncated and right-censored data are also allowed.
Proportional intensities regression models allow for covariates on each of
the 3 transitions. We use either a parametric approach with Weibull
baseline intensities or a semi-parametric approach with M-splines
approximation of baseline intensities in order to obtain smooth estimates.
Estimation of parameters is conducted by likelihood maximization in the
parametric approach or penalized likelihood maximization in the
||R (≥ 1.9.1)
||lava, mvtnorm, prodlim
||Celia Touraine, Pierre Joly, Thomas A. Gerds
||Thomas Alexander Gerds <tag at biostat.ku.dk>
||GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]