Quantcast

Maximization problem

classic Classic list List threaded Threaded
4 messages Options
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Maximization problem

Hobst
Hello Statalists

I need to maximize a log-likelihood function. I did this so far using Excel. (see the attached xls file). In the excel file there is only a 4x4 matrixand i could easily maximize the equation using the Excel solver. Also for a bigger matrix (37x37) it worked. But now i want to do this maximization on an even bigger Scale (300x300 Matrix) and the excel solver just isn't able to do it.

It would be great if somebody with MLE Programming skills could have look at the file i attached and give me some advise, if solving such a problem in Stata is possible at all (i have only basic programming skills) and how i could do this... Note that in the second table the diagonal entries contain different formulas then the off diagonals. The light blue shaded cells show the data structure i have in my Stata file.

Thank you very much for every kind of help, i would appreciate it a lot.

Regards, Toby

CM_optimization_Model.xls
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Maximization problem

nshephard
Administrator
1. Attachments to the list are deprecated (although in this instance
its been archived on the Nabble mirror for viewing as opposed to being
sent out to everyone).  See the FAQ linked in the footer of every
message to

2. Not everyone has the software to view M$'s proprietary file format.

3. I'd advise against using Excel for statistics, particularly issues
that arise from precision.  For further reasons and analysis of the
performance/accuracy of Excel for statistics see the resources listed
at http://slack.ser.man.ac.uk/progs/stata/avoid_excel.html (in
particular the articles from Computational Statistics & Data
Analysis).

4. I've not got the time to trawl through your spreadsheet work to see
if it might be do-able in Stata, and I doubt most others will either.
If you'd had a go at trying to implement it in Stata and were having
problems you might find people are willing/able to help with a
specific problem, but what you've asked is rather general and in my
opinion is expecting a lot from other members on the list.

I expect you can probably achieve what you want in Stata, but you're
going to have to learn how to program Stata/Mata.

Sorry if thats all a bit negative, just my opinion,

Neil

--
"... no scientific worker has a fixed level of significance at which
from year to year, and in all circumstances, he rejects hypotheses; he
rather gives his mind to each particular case in the light of his
evidence and his ideas." - Sir Ronald A. Fisher (1956)

Email - [hidden email]
Website - http://slack.ser.man.ac.uk/
Photos - http://www.flickr.com/photos/slackline/
*
*   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/
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Maximization problem

Hobst
Thank you for your reply. I am sorry for not obeiing the statalist rules, it will not happen again.  Thank you also for the links.
If you saying that it would be possible, that is already a big help. Then i will invenst some time learning Stata/Mata programming ( i now Excel is definitely NOT the way to go...)

Regards



On 22.07.2010, at 15:24, Neil Shephard wrote:

> 1. Attachments to the list are deprecated (although in this instance
> its been archived on the Nabble mirror for viewing as opposed to being
> sent out to everyone).  See the FAQ linked in the footer of every
> message to
>
> 2. Not everyone has the software to view M$'s proprietary file format.
>
> 3. I'd advise against using Excel for statistics, particularly issues
> that arise from precision.  For further reasons and analysis of the
> performance/accuracy of Excel for statistics see the resources listed
> at http://slack.ser.man.ac.uk/progs/stata/avoid_excel.html (in
> particular the articles from Computational Statistics & Data
> Analysis).
>
> 4. I've not got the time to trawl through your spreadsheet work to see
> if it might be do-able in Stata, and I doubt most others will either.
> If you'd had a go at trying to implement it in Stata and were having
> problems you might find people are willing/able to help with a
> specific problem, but what you've asked is rather general and in my
> opinion is expecting a lot from other members on the list.
>
> I expect you can probably achieve what you want in Stata, but you're
> going to have to learn how to program Stata/Mata.
>
> Sorry if thats all a bit negative, just my opinion,
>
> Neil
>
> --
> "... no scientific worker has a fixed level of significance at which
> from year to year, and in all circumstances, he rejects hypotheses; he
> rather gives his mind to each particular case in the light of his
> evidence and his ideas." - Sir Ronald A. Fisher (1956)
>
> Email - [hidden email]
> Website - http://slack.ser.man.ac.uk/
> Photos - http://www.flickr.com/photos/slackline/
> *
> *   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/
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Maximization problem

nshephard
Administrator
Forgot to add....

-man ml- would be a good place to start.

Good luck solving your problem.

Neil
--
"... no scientific worker has a fixed level of significance at which
from year to year, and in all circumstances, he rejects hypotheses; he
rather gives his mind to each particular case in the light of his
evidence and his ideas." - Sir Ronald A. Fisher (1956)

Email - [hidden email]
Website - http://slack.ser.man.ac.uk/
Photos - http://www.flickr.com/photos/slackline/
*
*   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/
Loading...