Hi,
I tried fitting
loglinear model using the glm(catspec). The data used is FHtab. . An
independence model was fitted. Here summary() and fitmacro( ) give different
values for AIC.
I understand that fitmacro( ) takes the likelilhood ratio L2(deviance)
to calculate AIC and uses the formula AIC= L2-
d.f(deviance)*2 and this AIC is used in nested models. (Am I right?)
The value given by loglik( ) is used by summary to
calculate AIC using the formula
AIC= -2 logL + K* e.d.f. Can anybody tell me how this log L is calculated?
It is not logL=Sum(ni* log (pi)), where
pi= fitted frequency / total no. of observations. The help available at extract
AIC( ) also is not giving the answer.
Please help
regards
Subha
[[alternative HTML version deleted]]
