gamlss.cens-package {gamlss.cens} | R Documentation |
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.
Package: | gamlss.cens |
Type: | Package |
Version: | 1.0 |
Date: | 2007-03-03 |
License: | GPL (version 2 or later) |
Mikis Stasinopoulos <d.stasinopoulos@londonmet.ac.uk> and Bob Rigby <r.rigby@londonmet.ac.uk>
Maintainer: Mikis Stasinopoulos <d.stasinopoulos@londonmet.ac.uk>
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.com/).
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.
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))