Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: r-square in -betafit-
From
SURYADIPTA ROY <[email protected]>
To
[email protected]
Subject
Re: st: r-square in -betafit-
Date
Mon, 21 Jun 2010 08:56:47 -0400
Dear Maarten,
Once again, thank you very much for these highly informative
discussions and suggestions!
Suryadipta.
On Mon, Jun 21, 2010 at 3:45 AM, Maarten buis <[email protected]> wrote:
> --- On Sun, 20/6/10, SURYADIPTA ROY wrote:
>> The AIC and the BIC values for the -betafit- model are
>> ( -773.5497, -729.3715), and that for OLS are (-478.2641,
>> -436.5402).
>
> Remember when dealing with *ICs: smaller is better, so in this
> case -betafit- is prefered.
>
> Anyhow the much better way to select models is to look at your
> data (graphs, graphs, and many many more graphs). I often find it
> useful not to focus on trying to find the best model, but instead
> try to understand where the differences between models come from.
> Then it will become obvious which one is the prefered summary of
> your data for your question. Notice what is a good summary
> depends on the question you want your model to answer, so don't
> get carried away by trying to get the "universally best model".
> Once the best model for your question is obvious, it will also
> be much easier to explain that to your audience.
>
> Hope this helps,
> 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/
>
*
* 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/