Last data update: 2014.03.03

R: The GAMLSS Add-On Package for Censored Data
gamlss.cens-packageR Documentation

The GAMLSS Add-On Package for Censored Data

Description

The purpose of this package is to allow the user of the GAMLSS models to be able to fit parametric distributions to data with censored or interval response variable.

Details

Package: gamlss.cens
Type: Package
Version: 1.0
Date: 2007-03-03
License: GPL (version 2 or later)

Author(s)

Mikis Stasinopoulos <d.stasinopoulos@londonmet.ac.uk> and Bob Rigby <r.rigby@londonmet.ac.uk>

Maintainer: Mikis Stasinopoulos <d.stasinopoulos@londonmet.ac.uk>

References

Rigby, R. A. and Stasinopoulos D. M. (2005). Generalized additive models for location, scale and shape,(with discussion), Appl. Statist., 54, part 3, pp 507-554.

Stasinopoulos D. M., Rigby R.A. and Akantziliotou C. (2006) Instructions on how to use the GAMLSS package in R. Accompanying documentation in the current GAMLSS help files, (see also http://www.gamlss.org/).

Stasinopoulos D. M. Rigby R.A. (2007) Generalized additive models for location scale and shape (GAMLSS) in R. Journal of Statistical Software, Vol. 23, Issue 7, Dec 2007, http://www.jstatsoft.org/v23/i07.

See Also

gamlss,gamlss.family

Examples

library(survival)
library(gamlss)
library(gamlss.dist)
# comparing results with package survival
# fitting the exponential distribution
ms1<-survreg(Surv(futime, fustat) ~ ecog.ps + rx, ovarian, 
             dist='exponential')
mg1<-gamlss(Surv(futime, fustat) ~ ecog.ps + rx, data=ovarian, 
             family=cens(EXP),c.crit=0.00001)
if(abs(-2*ms1$loglik[2]-deviance(mg1))>0.001) stop(paste("descrepancies in exp")) 
if(sum(coef(ms1)-coef(mg1))>0.001) warning(paste("descrepancies in coef in exp")) 
summary(ms1)
summary(mg1)
# fitting the Weibull distribution
ms2 <-survreg(Surv(futime, fustat) ~ ecog.ps + rx, ovarian, dist='weibull')
mg2 <-gamlss(Surv(futime, fustat) ~ ecog.ps + rx, data=ovarian, 
           family=cens(WEI, delta=c(0.001,0.001)), c.crit=0.00001)
if(abs(-2*ms2$loglik[2]-deviance(mg2))>0.005) 
     stop(paste("descrepancies in deviance in WEI")) 
summary(ms2);summary(mg2)
# compare the scale parameter
 1/exp(coef(mg2,"sigma"))
# now fit the Weibull in different parameterrazions  
mg21<-gamlss(Surv(futime, fustat) ~ ecog.ps + rx, data=ovarian, 
             family=cens(WEI2), method=mixed(2,30)) 
mg21<-gamlss(Surv(futime, fustat) ~ ecog.ps + rx, data=ovarian, 
             family=cens(WEI3)) 

Results