I have a quick question. How do you know when you have fitted a Bayesian
mixture model for two normals that the mixture 'fits' well. Is there some
Bayesian method that tells you how good the fit is? Secondly, if the data
is not on the entire real line, is it plausible to still use a mixture model
to get the components of the mixture?
--
Thanks,
Jim.
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|