Bookmark and Share

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: autometrics in Stata?


From   Stephen Martin <[email protected]>
To   [email protected]
Subject   Re: st: autometrics in Stata?
Date   Tue, 3 Sep 2013 18:38:00 +0100

Hi Maarten,

Thanks for your response.

I don't think that there's any "magic" involved in the autometrics
approach to model selection.  My understanding is that this merely
automates what the good analyst should be doing anyway but that it
speeds up the process.   For anyone interested, the paper that
stimulated my interest was:

Hendry D F and Krolzig H-M (2004).  "We ran one regression".  Oxford
Bulletin of Economics and Statistics, 66, 5, 799-810.

Steve


On 02/09/2013, Maarten Buis <[email protected]> wrote:
> You should feel free to make suggestions, and in fact the people from
> StataCorp have always said at Stata User Group meetings that
> immediately after a release is the best time for such suggestions as
> than they are still very open on what to do for the next release.
> Experience tells us that they will not tell us what they are working
> on, so you'll know whether it will be implemented in Stata 14 when
> Stata 14 is released. However, "automagic" model selection is
> typically not very popular in this community. In the end, it is the
> researcher that has to justify his model and (s)he cannot delegate
> that responsibility to a computer program. But, nothing stops you
> implementing this technique yourself if you want it badly enough. That
> is probably the most common reason why user written routines got
> written.
>
> -- Maarten
>
>
> On Mon, Sep 2, 2013 at 4:11 PM, Stephen Martin
> <[email protected]> wrote:
>> The 'autometrics' routine in PcGive offers an automated implementation
>> of David Hendry's general-to-specific modelling approach.  This
>> enables the analyst to start with a very general empirical model and
>> then refine this into a more parsimonious representation that passes
>> various standard econometric tests.
>>
>> Is there an equivalent command in Stata 13?
>>
>> If not, may I suggest consideration be given to adding this to Stata 14?
>>
>> Thanks.
>>
>> Steve
>> *
>> *   For searches and help try:
>> *   http://www.stata.com/help.cgi?search
>> *   http://www.stata.com/support/faqs/resources/statalist-faq/
>> *   http://www.ats.ucla.edu/stat/stata/
>
>
>
> --
> ---------------------------------
> Maarten L. Buis
> WZB
> Reichpietschufer 50
> 10785 Berlin
> Germany
>
> http://www.maartenbuis.nl
> ---------------------------------
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/
>


-- 
Stephen Martin
Research Fellow
Department of Economics
University of York
Heslington
YORK  YO10 5DD
UK

Tel:  00 44 1904 433706
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index