Skip to content
Prev 4089 / 398506 Next

GLM query

[...]
AIC: -70.016
Here's my guess.  Your AIC is based on a log-likelihood regarding log(GDP)
as the data, and his is regarding GDP as the data. The transformation
of the density adds a term to the log-likelihood which is the same for each 
model.

Test:
[1] 324.4009

seems close enough to the difference, although I would have expected it
to be closer.