Thanks to Kit Baum, -betafit- has been updated on
SSC.
-betafit- is for those fitting beta distributions,
with or without covariates.
In 1997 I wrote a -beta- for fitting a beta
distribution by ML without covariates. This program
is still part of -betafit- as -beta4-, and it
should work with Stata 4 upwards. This didn't use
-ml-: it was a fairly straight port of an algorithm
published in Journal of Applied Meteorology by
P.W. Mielke in 1975.
In 2003, riding on the back of some work by Stephen
Jenkins on other distributions, I wrote a new -betafit-
that now took covariates if specified. But it
stuck to the parameterisation of a beta distribution
in terms of two shape parameters.
Every now and again threads on Statalist ask what
should be done when the response is a continuous
proportion between 0 and 1, and sooner or later
someone mentions the beta distribution as one
possibility. Recently Maarten Buis pointed that
the existing parameterisation of -betafot- was not particularly
useful for problems with covariates.
Now Maarten has come on board, taking the initiative
in implementing an extra parameterisation in terms
of a location and a scale parameter. -betafit-
is now attributable to Cox, Jenkins and Buis.
-betafit- now requires Stata 8.2, which is
a slight increase on the 2003 version, but
those with access to Stata 8 should be able
to upgrade to Stata 8.2 at least.
We also added some interesting references to
the help file.
The authors think that -betafit- is beta at doing
what it claims to do. Whether it is a beta solution
for your problem than alternatives (such as the
GLM approach recommended by Papke and Wooldridge
Journal of Applied Econometrics, 1996) is for
you to judge.
Nick
[email protected]
*
* 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/
