Thank you very much for your response. But the problem still remained. I obtained my distribution parameters for all diameter data (without lump).I sow that you create the fitted freq using a difference from the neighborhood classes (8-4), but I have a huge interval from 96 fo 4. If I put diff(pgamma(c(96,8), shape, rate)) I obtaining the same values for all classes.
Thank you very much for your help! Best regards! On 26 February 2016 at 14:41, Duncan Murdoch <murdoch.dun...@gmail.com> wrote: > On 26/02/2016 4:09 AM, catalin roibu wrote: > >> I'm working in forestry research and need the fitting distribution for >> forest structure in relation with diameter. >> The tree diameter have been lumped into 4 cm diameter classes, forming the >> diameter experimental distribution. >> For fitting I used the gamma distribution and I obtained the distribution >> parameters (scale and rate). After that I used the dgamma function and I >> have the pdf values. My question is how to obtain fitted absolute >> frequency >> to compare with the true frequency? >> > > Since you're lumping into classes, you don't want the density, you want > differences in the cumulative probability. So if your class runs from 4 to > 8 cm, use something like > > pgamma(8, shape, rate) - pgamma(4, shape, rate) > > or the equivalent but a little obscure > > diff(pgamma(c(8, 4), shape, rate)) > > Duncan Murdoch > > P.S. Please keep discussion on the mailing list. I've cc'd this response > there. > > > -- - - Catalin-Constantin ROIBU Lecturer PhD, Forestry engineer Forestry Faculty of Suceava Str. Universitatii no. 13, Suceava, 720229, Romania office phone +4 0230 52 29 78, ext. 531 mobile phone +4 0745 53 18 01 FAX: +4 0230 52 16 64 silvic.usv.ro <http://www.usv.ro/> [[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.
