-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 "Shaw, Ewart" <[EMAIL PROTECTED]> writes:
> I think Mike Day's probably right in recommending following up links > between J, R & BUGS. Note also the recently published (August 2007) > paperback "Bayesian Computation with R" by Jim Albert - but beware of > misprints etc.! Ewart, Thanks. I'll have to put that on my to-read list. I'm currently reading a book on hierarchical modeling by Gelman and Hill, and I've skimmed Gelman's Bayesian Data Analysis; that's on my to-read list for later. > MCMC is inherently iterative, and can be relatively slow in J. > However, it can also be relatively slow in SPlus, R or any other > system. Some MCMC techniques such as "adaptive direction search" and > "multiple try" methods are more suitable for parallelisation. My I've done a bit of playing with OpenBugs; most of my attempts at MCMC have been with MCSim. > user-unfriendly code for this will be upgraded from J3.05 Real Soon > Now! [I'm the still small Bayesian voice that uses cubature methods > in preference to MCMC.] More to learn; thanks (I think :-). Let us know when your code is ready for J6.x, if you don't mind. Bill - -- Bill Harris http://facilitatedsystems.com/weblog/ Facilitated Systems Everett, WA 98208 USA http://facilitatedsystems.com/ phone: +1 425 337-5541 -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (MingW32) Comment: For more information, see http://www.gnupg.org iD8DBQFHIVWX3J3HaQTDvd8RAlOIAJwPYrvFBm6oMis53t5lt2/jXVpBvACfdC0e VQiJqO4L4dvEc04SL3w/Dx4= =ZmAL -----END PGP SIGNATURE----- ---------------------------------------------------------------------- For information about J forums see http://www.jsoftware.com/forums.htm
