Dear all,
Is it possible to calculate AIC
from an output for "gam"?
"gam" outputs deviance and dispersion.
Although I came across an equation of
AIC = deviance/n + 2*df*deviance/(n-df)/n,
AIC obtained from this calculation was
1000 times larger than the AIC generated
by an equally predictive "glm" model.
Sincerely
Yoshiro Nagao
--------------------------------------
Easy + Joy + Powerful = Yahoo! Bookmarks x Toolbar
http://pr.mail.yahoo.co.jp/toolbar/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
