st: Re: formula for AIC in Stata

[Kit Baum <baum@bc.edu>]

Dirk said

try to open the -arimafit.ado- file in your STATA program folder and  
have a
look for the formula. Why are you interested in that?


arimafit is a user-written routine, available from SSC. You may

ssc type arimafit.ado

and you will find the line

 local aic `ll2'+2*`np'

where ll2 is minus twice the likelihood value and np is the number of  
parameters. In 1998, official Stata did not calculate the AIC.  Now,  
it does, with the estat command. As another poster wrote,

AIC = -2*ln(L)+2*p

where ln(L) is the log-likelihood of the model and p is the number of
parameters.


Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html


On Oct 26, 2005, at 2:33 AM, statalist-digest wrote:


> try to open the -arimafit.ado- file in your STATA program folder  
> and have a
> look for the formula. Why are you interested in that?
*
*   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/