This is off-topic (apologies), but I thought I might get a lead or two
here.
I'm interested in generating random deviates from a multivariate
distribution which is a generalization of the beta distribution -- the
Bayesian canonical distribution for the parameter estimates of a
multinomial distribution. Given a vector (length n-1) of probabilities p
and a vector (length n) of shape parameters x (which would correspond to
the observed multinomial frequencies in a sample),
P(p,x) = ((sum(x)+1)!/(x1! ... x(n)!) * p(1)^x(1) * ... * (1-sum(p))^x(n)
Does this distribution have a name?
Can anyone point me to a way of sampling it? Has this been done?
(Canned, or semi-canned, or translatable methods would be super ...) I was
thinking about doing a very inefficient rejection sample ... I poked
around in science citation index on references citing the CACM paper by
Cheng that's cited in rbeta.c, but didn't find anything immediately
useful.
thanks,
Ben Bolker
--
--------------------------------------------
Ben Bolker bolker at zoo.ufl.edu
Zoology Department, University of Florida http://www.zoo.ufl.edu/bolker
318 Carr Hall/Box 118525 tel: (352) 392-5697
Gainesville, FL 32611-8525 fax: (352) 392-3704
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at
stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
