Giovanni:
The beta distribution is a good place to start, since the Dirichlet is a multivariate
extension of the beta distribution. It's easier to start with the univariate case and
than work up to the multivariate case. The references below (which are also in
the help-file) are a good applied way to start with the beta distribution.
I'd be interested in your results. Having examples from multiple disciplines is
always handy.
HTH,
Maarten
Ferrari, S.L.P. and Cribari-Neto, F. 2004. Beta regression for modelling rates and
proportions. Journal of Applied Statistics 31(7): 799-815.
Paolino, P. 2001. Maximum likelihood estimation of models with beta-distributed
dependent variables. Political Analysis 9(4): 325-346.
http://polmeth.wustl.edu/polanalysis/vol/9/WV008-Paolino.pdf
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z214
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
-----Original Message-----
From: [email protected] [mailto:[email protected]]On Behalf Of Giovanni Vecchi
Sent: donderdag 1 juni 2006 15:10
To: [email protected]
Subject: st: RE: RE: sureg? ml? system with adding-up constraint
I'll experiment with your program... after studying the Dirichlet
distribution, about which I am fully ignorant.
Your help has been really appreciated.
*
* 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/
