On Dec 4, 2014, at 6:55 PM, dila radi wrote: > Dear R users, > > I am looking to fit a gamma curve onto a histogram of the data. > > Consider dt1 as my data: > c(203.9, 91.5, 24.5, 34.5, 164, 144, 160.5, 195, 191.5, 189, > 133, 110.5, 155, 80.5, 250.5, 116, 145, 118.5, 406, 183.5, 142.5, > 197, 367, 134, 153.5) > > I am using this code in R > x<-dt1 > h<-hist(x,breaks=seq(0,500,25),col=rgb(0,0,1), plot=F) > h$counts <- h$counts / sum(h$counts) > plot(h, freq=TRUE, ylab="Relative Frequency", xlab="Rainfall (mm)", > main = 'Histogram KBU-ML Gamma Disribution') > est <- fitdistr(dt1,"gamma")$estimate > curve(dgamma(x, rate=0.02220921, shape=3.63421746),from=0, to=500, > main="Gamma distribution", add = T, col = "red") > > but the gamma fit is not fitted onto histogram as much as it supposed to > be. How should I overcome this? > First read ?hist. Then set freq=FALSE. Then you will be comparing "like to like".
Otherwise you cna just hack it by multiplying the dgamma expression by 25. > sum(h$counts) #before the standardization [1] 25 > Thank you in advanced. > > Dila > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. David Winsemius Alameda, CA, USA ______________________________________________ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
