[S] MCMC length

Xu Fan (fan@stat.cmu.edu)
Wed, 6 May 1998 22:43:16 -0400 (EDT)


How long should the chain be for a 10-dimensional parameter? Any ideas
on proposal distribution? For example, if I choose normal, how large
should the variance be?

Thank for the previous replies on ms starting value. I turn to MCMC
for an approximate solution. It is however time-consuming.

-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news