Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: non-linear models not converging


From   Maarten Buis <maartenlbuis@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: non-linear models not converging
Date   Wed, 22 May 2013 15:08:19 +0200

One trick that often helps with this kind of model is to make sure
that all independent/explanatory/right-hand-side/x-variables have the
value 0 at a meaningful point within (or near) the range of the data.
So don't use "year of birth in years since the year 0" but for example
"year of birth in decades since 1950" ( = (year of birth - 1950 ) / 10
). The logic is that these models add a model for the constant. If
that refers to a point way outside the range of the data, it sometimes
becomes difficult.

On Wed, May 22, 2013 at 2:56 PM, James Bernard <jamesstatalist@gmail.com> wrote:
> Thanks both,
>
> I am running -xtpoisson random effect.... it does not converge!
>
> Thanks,
> James
>
>
> On Wed, May 22, 2013 at 8:53 PM, Kelvin Mulungu
> <kelvin.statalist@gmail.com> wrote:
>> Bernard,
>>
>> I had the same problem sometime last week. Am not sure this is a
>> standard solution but it worked for me. Start simple- begin with
>> simple models in the line of your problem and build on to the
>> complicated model you want run and see where exactly the model will
>> stop converging. Add variables in a step-wise fashion, i.e. start with
>> what you think are the most crucial variables and lets say begin with
>> two and keep adding the variables you think influence your Y.
>>
>> Finally, check your data to make sure it can handle that type of
>> model. In some cases, the data may not allow you to run such a model.
>>
>> Hope this helps, though am not sure what type of non-linear model you
>> are trying to run.
>>
>> On Wed, May 22, 2013 at 3:43 PM, James Bernard <jamesstatalist@gmail.com> wrote:
>>> Hi all,
>>>
>>> I understand that the numeric methods used for estimation of models in
>>> Stata (and any other package) may result in a model that does not
>>> converge.
>>>
>>> Do you happen to know of any trick to help make the model converge? To
>>> increase the chance of converging?
>>>
>>> Thanks,
>>> James
>>> *
>>> *   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/
>> *
>> *   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/
> *
> *   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/


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