[R] R-help; Censoring

David Winsemius dwinsemius at comcast.net
Wed Apr 11 06:27:26 CEST 2012


On Apr 10, 2012, at 11:48 PM, Christopher Kelvin wrote:

> Hello,
> I wish to censor 10% of my sample units of 50 from a Weibull  
> distribution. Below is the code for it.
> I will need to know whether what i have done is correct and if not,  
> can i have any suggestion to improve it?
> Thank you
>
>  p=2;b=120
> n=50
> r=45
>
> t<-rweibull(r,shape=p,scale=b)
> meantrue<-gamma(1+(1/p))*b
> meantrue
>
> cen<- runif(n-r,min=0,max=meantrue)
> cen

I don't see how that works. You have five random draws from a uniform  
distribution with support on some interval, not necessarily related to  
the t vector. How are you deciding which of the variates should be  
considered censored? Why wouldn't you just use set.seed(n); cens <-  
sample(1:50, 5)) and use as an index?


-- 
David Winsemius, MD
West Hartford, CT



More information about the R-help mailing list