Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: formula for AIC in Stata


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: formula for AIC in Stata
Date   Wed, 26 Oct 2005 07:50:51 -0400

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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index