Skip to content

DIC of SAR model

3 messages · Milan Sharma, Pascal Oettli, Roger Bivand

#
On Thu, 26 Sep 2013, Pascal Oettli wrote:

            
The underlying question is whether the paper fitted the simultaneous 
autoregressive model (spatial error model, SEM), or the spatial lag model 
(a.k.a. SAR) using Bayesian methods. If it did, then reporting DIC seems 
possibly sensible, if it used ML, it doesn't make much sense anyway. All 
kinds of odd things appear in published work, it's worth thinking through 
whether they should be there.

Roger