Re: st: ML program in Stata 12.1 for a nonlinear equation of the form Y=F(x)*G(z)

[Antony Chapoto <achapoto@gmail.com>]

Thanks a lot Jay.  Let me try out -nl-.

Antony

On Sun, Apr 7, 2013 at 1:09 AM, JVerkuilen (Gmail)
<jvverkuilen@gmail.com> wrote:
> On Sat, Apr 6, 2013 at 4:35 PM, Antony Chapoto <achapoto@gmail.com> wrote:
>
>>
>> I would like your assistance to write an ML program in Stata 12.1 for
>> the following nonlinear model:
>>
>> <snip>
>
> This doesn't directly answer your question, but if I'm not mistaken,
> this model could be estimated using -nl-, which is specialized for the
> problem of nonlinear regressions with Gaussian errors, and thus has
> useful post-estimation, etc. I'm a little worried that -nl- (or -ml-?)
> doesn't have an option for a regularized method (such as
> Levenberg-Marquardt), though, given how complicated your model is due
> to the G(z) term.
>
> That said, it looks like an unusual model with many parameters in
> which homoscedastic Gaussian errors seem potentially dubious, and is
> likely to have some difficulty estimating simply on numeric grounds.
> I'd definitely try some pro-active simulation of likely values of the
> variables.
>
> Jay
> --
> JVVerkuilen, PhD
> jvverkuilen@gmail.com
>
> "It is like a finger pointing away to the moon. Do not concentrate on the
> finger or you will miss all that heavenly glory." --Bruce Lee, Enter the
> Dragon (1973)
> *
> *   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/



-- 
Antony Chapoto, PhD
Post Doctoral Research Associate
Food Security Research Project
Michigan State University
Department of Agricultural Economics
Ag  Hall 50
East Lansing, MI 48824
Phone: 517-353-1851 (0)
           517-402-3569 (C)
*
*   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/