Re: st: Symbolic differentiation

["E. Paul Wileyto" <epw@mail.med.upenn.edu>]

This is done using nlcom. Derivatives will be approximated numerically. 
You specify the non-linear combination of parameters you want, and you 
get back a point estimate, and standard errors. Covariance matrix can be 
seen by typing

-return list-

Paul


John Bates wrote:
> Is there any way to do symbolic differentiation in Stata or Mata?  i.e., deriv(x^2)=2x?
>
> Related to this question: suppose I regress y on x and z and want to estimate the variance of x_hat/z_hat.  Are there any commands that let you calculate the variance of this expression automatically?  (I'd like to avoid calculating the first-order taylor expansion etc. myself, especially for more complicated expressions).
>
>
>
>       
>
> *
> *   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/
>
>   

--
E. Paul Wileyto, Ph.D.
Assistant Professor of Biostatistics
Tobacco Use Research Center
School of Medicine, U. of Pennsylvania
3535 Market Street, Suite 4100
Philadelphia, PA  19104-3309

215-746-7147
Fax: 215-746-7140
epw@mail.med.upenn.edu 

*
*   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/