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.
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))