Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: RE: Selection of distribution
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: RE: Selection of distribution
Date
Tue, 28 Aug 2012 09:11:45 +0100
-betafit- and -gammafit- are from SSC. There are planty more such
commands on SSC for other distributions, including all of those named
by Alan.
Nick
On Mon, Aug 27, 2012 at 10:17 PM, Feiveson, Alan H. (JSC-SK311)
<[email protected]> wrote:
> Well, for the beta and gamma distributions, you can use -betafit- and -gammafit_ repsectively. Also, for the Weibull, log normal, inverse gaussian or other distributions supported by -streg-, you can use -streg- after -stset- (assuming all observations are "failures"). These all give maximum likelihood estimates of the parameters. Other methods are possible, e.g. method of moments, etc.
Paul Millar
> Are there any commands that, given a variable with empirical values,
> will select the distribution which best fits those values? For the
> gamma distribution (for example) is there a program (user-written or
> otherwise) that will tell me which parameters of a density function
> will best fit the data?
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/