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]
[no subject]
Theoretically, it is possible that -ml search- produced random
starting values that led to a different local maximum.
On Tue, May 4, 2010 at 12:13 PM, Valerie Orozco
<[email protected]> wrote:
> I use some macros to call the variables into the ml, but they don't change after estimation.
> So "re"running the same ml program should give me the same results each time...
> Thus, I still don't understand what I forgot...
>
>
> -----Message d'origine-----
> From Maarten buis <[email protected]>
> To [email protected]
> Subject Re: st: why one ml program doesn't give the same results twice ?
> Date Tue, 4 May 2010 09:19:01 +0000 (GMT)
>
> --- On Tue, 4/5/10, Valerie Orozco wrote:
>> It seems some "saved" results still remain and affect the
>> second estimation. What did I forget to clear ?
>
> Did you pass some information to the evaluator using global
> macros? If so, you might want to start your program (not
> your evaluator) with -macro drop _all- (or -macro drop S_*-
> if you know that all the global macros you use start with
> S_).
>
> Hope this helps,
> Maarten
>
> -----Message d'origine-----
> De : Valerie Orozco
> Envoyé : mardi 4 mai 2010 11:07
> À : [email protected]
> Objet : why one ml program doesn't give the same results twice ?
>
> Hi,
>
> I wonder why a whole ml program doesn't give the same results twice in one Stata session ?
> That is, doing the following steps doesn't give the same estimation :
>
> 1) Run my ml model and ml maximize
> 2) Clear all (mat drop _all + ereturn clear + ml clear)
> 3) "Re"run my ml model and ml maximize
>
> It seems some "saved" results still remain and affect the second estimation. What did I forget to clear ?
> (if I close the Stata session and open another one, it gives the same results)
>
> Thank you very much for your help.
>
> valérie
>
> -------------------------------
> Valérie OROZCO
> Toulouse School of Economics (INRA-GREMAQ)
> 21, allée de Brienne
> F-31000 Toulouse, France
>
> MA 101
> +33 5 61 12 85 91
> -------------------------------
>
>
> *
> * 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/
>
--
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.
*
* 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/
* References:
o st: RE: st :why one ml program doesn't give the same results twice ?
+ From: Valerie Orozco <[email protected]>
* Prev by Date: Re: st: Survey question
* Next by Date: Re: st: Survey question
* Previous by thread: st: RE: st :why one ml program doesn't give the same results twice ?
* Next by thread: [no subject]
* Index(es):
o Date
o Thread
© Copyright 1996-2010 StataCorp LP | Terms of use | Privacy | Contact us | Site index
*
* 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/