Re: FW: st: Comparing the similar model (but one in level and the other after taking the 1st difference)

[Maarten Buis <maartenlbuis@gmail.com>]

--- On Tue, Jan 24, 2012 at 1:28 AM, Almutairi T. wrote:
>>> I estimated the same model twice, but one in level and the other after taking the 1st difference (to get rid of AR1)
>>>
>>> I am looking for a goodness of fit measure for pooled time
>>> series models  other than R^2 (as it is not suitable for model with unsimilar dependent variable)
>>>
>>> Does log-likelihood values (and BIC or AIC) suitable to compare b/w these 2 models?

--- Maarten Buis wrote:
>> No, that to depends on the scale of the dependent variable, see for
>> example: <http://blog.stata.com/2011/02/16/positive-log-likelihood-values-happen/>

On Tue, Jan 24, 2012 at 4:08 PM, Almutairi T. wrote:
> I cant see any relation b/w my question and the link (Positive log-likelihood values happen), please explain further.

Please do not respond privately. The reasons for that are discussed in
the Statalist FAQ
<http://www.stata.com/support/faqs/res/statalist.html#private>.

The main point is actually Nick's comment on that blog post. In short:
likelihoods have units of measurement and this unit of measurement is
derived from the unit of measurement of the dependent variable. So the
unit of measurement of two likelihoods from models with dependent
variables with different units of measurement will be different, and
these likelihoods can thus not be compared.

-- Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany


http://www.maartenbuis.nl
--------------------------
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/