[R] 95% Confidence Interval for a p-p plot

pablo.castano pablo.castano at cardif.com.co
Mon Apr 1 19:41:15 CEST 2013


I want to create upper and lower 95% confidence intervals for a p-p plot of
an empirical distribution with a theoretical gamma distribution.

This is my code: 

x<-rgamma(100,shape=2, rate=1) # empirical data
fitdistr(x,"gamma") # fit a gamma distribution
dist<-pgamma(x,shape=1.9884256 ,rate=0.8765314 ) # fitted distribution,
using the loglikelihood estimated parameters plot(ppoints(n=100),
sort(dist)) # create p-p plot 
abline(0,1) # diagonal line to check fit

Is there an implementation of the delta method in R that I could use for
this in order to estimate the variance of the predicted probability ?


View this message in context: http://r.789695.n4.nabble.com/95-Confidence-Interval-for-a-p-p-plot-tp4662982.html
Sent from the R help mailing list archive at Nabble.com.

More information about the R-help mailing list