[R] GLM query

[Prof Brian Ripley]

> From: spoon <spoon at hilbert.maths.utas.edu.au>
> Date: Tue, 21 Dec 1999 19:30:40 +1100 (EST)
> 

[...]
AIC: -70.016
 
> But I get a very different AIC to Lindsey (he gets 254.3).  I've
> played around a bit and have no idea how to get his solution.  Any
> clues?

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:

> 2*sum(log(gdp$GDP))
[1] 324.4009

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

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._