[R-sig-ME] Question about usuge of DIC

[desja004 at umn.edu]

Hi,
I have a general question about the use of the DIC and other fit indices. I 
have fit a Poisson and a zero-inflated Poisson model in MCMCglmm and I am 
curious if I can use the DIC as evidence in support of one distributional 
model over another (with the same fixed and random effects)? Currently I 
plan on including graphs with predicted values from the two models to show 
that the ZIP model fits better than the Poisson but I was curious if I 
could use the DIC or another statistic to support my decision in choosing 
one distribution over another.
Chris