Whit,

Here is what the version 8.0 documentation states about computation of AIC and SBC.

Information Criteria AIC and SBC

The Akaike's information criterion (AIC) and the Schwarz's Bayesian information criterion (SBC) are computed as follows:

AIC = -2ln(L) + 2 k SBC = -2ln(L) + ln(N) k

In these formulas, L is the value of the likelihood function evaluated at the parameter estimates, N is the number of observations, and k is the number of estimated parameters. Refer to Judge et al. (1985) and Schwarz (1978) for additional details.

I have not used AUTOREG before and don't know what sort of model is being fit, so I don't know exactly how the likelihood is constructed. But the formula for AIC is a standard formula. Given that the likelihood is properly constructed, then the AIC statistic is reasonable. Note that in this construction, AIC has interpretation that smaller AIC is better.

Dale

--- Whit Johnson <wjohnson@COLORADO.EDU> wrote: > Hello, > I am trying to find documentation on how AIC is calculated in proc > Autoreg. > I have calculated AIC by using the formula in Burnham & Anderson, and > I > get a much different result than in the SAS output. > thanks for any help.

===== --------------------------------------- Dale McLerran Fred Hutchinson Cancer Research Center mailto: dmclerra@fhcrc.org Ph: (206) 667-2926 Fax: (206) 667-5977 ---------------------------------------

__________________________________ Do you Yahoo!? Yahoo! SiteBuilder - Free, easy-to-use web site design software http://sitebuilder.yahoo.com