Re: Help on comparing models

["Lucke, Joseph F" <LUCKE@uthscsa.edu>]

Rui

The following contains some of the issues, but their intuitive generalization of the AIC is not correct, I read somewhere.

Joe

 

Burnham, K. P., & Anderson, D. R. (1998). Model selection and inference: A practical information-theoretic approach. New York: Springer.

-----Original Message-----
From: rui zhang [mailto:rzhang@spatial.maine.edu]
Sent: Monday, December 08, 2003 9:13 PM
To: s-news
Subject: [S] Help on comparing models

Hi, all

 

I am thinking about using two models to fit the observations, one

is polynomial model

fit1: catch~long+lat+long^2+lat^2+long*lat

the other is exponential model

fit2: catch~alpha*exp((long-lat)^2)+beta

But I do not know how to prove the hypothesis that fit2 is better than

fit1.

Can I use the function anova(fit2, fit1)?

 

Thanks a lot!

 

yours,
rui

 

-----------------------------------------------------------------
Rui Zhang
Department of Spatial Information Science and Engineering
5711 Boardman Hall, Room 248
University of Maine
Orono, ME 04469-5711
USA
email:rzhang@spatial.maine.edu
home:www.spatial.maine.edu/~rzhang