[R] parameters in fitdistr

From: Carsten Steinhoff <carsten.steinhoff_at_gmx.de>
Date: Wed 07 Jun 2006 - 00:09:17 EST


today I've updated from Version 2.1.1 to 2.3.1.

The function you can find below for MLE with double tuncated Lognormal Distr. is working very well with 2.1.1 but now with the same function I get the error: object "u_right" not found ... although I've declared standard-values. I also tryed it with the call: my.lnvfit(rlnorm(1000,5,2),u_left=100,u_right=10000)!

Is it due to changes in the environment or in the function "fitdistr" (MASS) ?
For both I could not find anything regarding this problem in the documentation.

Who can help?

Thanks a lot,

lognormal_tr=function (loss, u_left=0, u_right=Inf, mu=NA, sigma=NA, ...)


verluste=which(loss>=u_left & loss <=u_right) loss=loss[verluste]

if (is.na(mu))
mu = mean(log(loss))
if (is.na(sigma)) 

sigma = sd (log(loss))

# Function to optimize


return(dlnorm(x,mu,sigma)/(plnorm(right,mu,sigma)-plnorm(left,mu,sigma))) }

pars=fitdistr(loss,lnv2,list(mu=mu,sigma=sigma),left=u_left,right=u_right, ...)
return(mu=as.vector(pars$estimate[1]), sigma=as.vector(pars$estimate[2])) }

R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Wed Jun 07 01:23:56 2006

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Wed 07 Jun 2006 - 02:10:36 EST.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.