|
|  |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Stata and Bayesian capabilities?
As a faculty in the department that's about half Bayesian, I would
disagree with Nick's characterization of Bayesian methods as unstable
-- the discussion about the objective priors is still going on, while
the MCMC paradigm is there to stay, because it is so computationally
efficient. The thing is, as soon as you move away from the mean of the
i.i.d. sample, things are beginning to become more of the art of
writing efficient samplers that of course tend to be problem-specific,
thus getting into the domain of the cutting edge research rather than
mainstream packaging -- you really need to know all of the basic
statistics, plus the Bayesian version of it, plus understand
computational challenges, before you begin to get good (quickly
converging, efficiently mixing, etc.) results for a moderate
complexity model at hand.
WinBUGS is the largest available piece of software (and it's free),
and as long as it is written in C originally, it it can probably be
compiled as a Stata plug-in :)). WinBUGS is R-callable, so folks using
R won't bother looking for anything else. SAS is just beginning to
incorporate those estimation methods for a very restricted set of
procedures -- and you can get the likelihood solutions for those just
as well, there is not that much terribly interesting there in the
sense of the Bayesian methods beating the frequentist ones.
As a bottom line, I agree with NJC that the Stata world would be
better off with the development resources spent on something more
mainstreamy and applicable by the users of the data.
On 4/29/07, n j cox <[email protected]> wrote:
We need a sharp distinction here between what StataCorp will (or
according to some, should) do and what users might do. Well, users
can program what they like and they are not obviously going Bayesian
within the Stata community. Admittedly, it would take a brave and bold
Stata programmer to start cloning WinBUGS, but I don't detect much
interest even, and if few users care, why should StataCorp?
My own guess is that StataCorp are most unlikely to go Bayesian in any
serious way in any foreseeable future. The lack of interest that is
evident (or, if you prefer, not evident) arises from a mix of academic
and marketing reasons.
StataCorp developers are more academic than most academics in pursuing
stuff they find interesting and ignoring stuff they don't, and the good
folks at StataCorp aren't (detectably) that interested. What the good
folks a few kilometres [miles] away at Texas A and M are interested in
is neither here nor there given that. This kind of development just
cannot be done by talking to, or even commissioning, a few outside experts.
Also, the fact that Bayesian statistics are on a roll within
mathematical statistics is not that crucial. Some (small scale)
statistical advances can be implemented in Stata as soon as a paper is
published. With other (large scale) developments the prudent thing is to
wait ten or twenty years to see what, if anything, emerges as, long
term, part of the landscape. Otherwise, StataCorp wastes everybody's
time (and money) implementing stuff that was bang up-to-date last year,
but already very dated next year.
I am not clear that Bayesian statistics is that stable. In fact, in some
ways it is in retreat, not a story that is prominent, but bear with
me. A few decades ago all the emphasis was on identifying your
personalistic (subjective) probabilities, writing down your own loss
functions, stating your coherent bets, whatever, but where has all that
gone? Down the drain of discarded dogmas. These days, when people are
talking about Bayesian statistics, more and more it seems that they are
talking about a branch of numerical analysis. More importantly, when the
textbooks start telling more or less the same story, then we will have
some stability. At present, most of the supposed textbooks look more
like research monographs to me.
--
Stas Kolenikov
http://stas.kolenikov.name
*
* 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/
