Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Investigating distributional characteristics


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Investigating distributional characteristics
Date   Sun, 7 Aug 2005 18:51:07 +0100

The most obvious alternative is your 
cloning -gammafit- and -qgamma- and changing
them for this distribution. Giving the 
pdf, plotting the density is naturally easier. 

Nick 
n.j.cox@durham.ac.uk 

Naji Nassar
 
> I'm used to combine several commands in order to investigate 
> distributional characteristics
> Example for a continuous variable with Gamma or lognormal 
> distribution. 
> gammafit x
> generate gamdenx=gammaden(e(alpha),e(beta),0,x)
> qgamma x, gen(qgamx)
> sort x
> twoway (hist x) (line gamdenx x) (other densities) name(hist)
> twoway (scatter qgam1 x) (scatter other quantiles) name(quan)
> combine hist quan
> 
> I'd like to test other formal adhoc distributions, ie 
> truncated gamma (at 1)
> prob(x)=Fgamma(rate,x)/(1-Sgamma(rate,t<1))
> 
> Thanks for your help (fitting the truncated distribution, 
> estimating density & quantiles)

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index