Filter
Top Products
331
Specification Search
Madigan and Raftery (1994) suggest that only models in Occam’s window be used
for purposes of model averaging (a topic not discussed here). The symmetric Occam’s
window is the subset of models obtained by excluding models that are much less
probable (Madigan and Raftery suggest something like 20 times less probable) than the
most probable model. In this example, the symmetric Occam’s window contains
models 7, 6, and 8 because these are the models whose probabilities (BIC
p
values) are
greater than .
Rescaling the Bayes Factors
E On the Current results tab of the Options dialog box, select Akaike weights / Bayes factors
(max = 1)
in the BCC, AIC, BIC group.
In the table of fit measures, the column that was labeled BIC
p
is now labeled BIC
L
and
contains Bayes factors scaled so that the largest value is 1. This makes it easier to pick
out Occam’s window. It consists of models whose BIC
L
values are greater than
; in other words, Models 7, 6, and 8. The L subscript on BIC
L
is a
reminder that the analogous statistic BCC
L
can be interpreted as a likelihood.
0.860 20⁄ 0.043=
120⁄ 0.05=