One thing you could do is to use restricted cubic splines. This is a
way to allow for a very flexible relationships though it is strictly
speaking not semi-parametric. Afterwards you could use the
-postrcspline- package downloadable from -ssc- with the -force- option.
-- Maarten
--- Mahesh Ramachandran <[email protected]> wrote:
> Hello Maarten:
>
> Thanks for the reply. I will give a brief overview of what I am
> trying to do, perhaps you or someone can point
> me in the right direction. I am trying to estimate a demand model,
> where the dependent variable consumption
> and have a several independent variables. The intention is to compare
> estimates from several functional
> forms to nonparametric estimation. Due to the curse of
> dimensionality, I am trying instead to estimate a
> semiparametric regression, where I am intend to treat one of the
> independent variable as nonparamteric
> others linear. If -plreg- does not work for panel data could you
> suggest any alternatives?
>
> P.S:
>
> The syntax error was from trying to estimate the example
> (Dr.Yatchew's dataset)from the article
> "Semi-parametric difference-based estimation of partial linear
> regression models" by Michael Lokshin. I used
> same dataset and command, still got error message. Did all the usual
> checks, unable to locate the error in
> the syntax. Here is the command from Dr.Lokshin's article:
>
> use plreg_example, clear;
> plreg tc wage pcap puc kwh life lf kmwire, nlf(cust) gen(func) bw(1);
>
>
>
>
> --- Mahesh Ramachandran <[email protected]> wrote:
> > I am trying to estimate a semiparametric regression for a panel
> > dataset. Could you advise me on the command to use. I tried "plreg"
> ,
> > for some reason it is giving me "syntax error".
>
> I don't think that there is much stuff on semiparametric regression
> for
> panel data in Stata. -plreg- certainly was not intended for panel
> data,
> as you can read in (Lokshin 2006).
>
> Anyhow, if you want help on what you did wrong with -plreg- you will
> have to tell us exactly what you typed. All we know now is that you
> have somehow not used the correct syntax (which you could have
> guessed
> yourself from the error message), and all we can say is that you
> should
> have used the correct syntax (which you also could have guessed), but
> because you have not told us what syntax you have used we cannot tell
> you where you have made a mistake...
>
> -- Maarten
>
> Michael Lokshin (2006) "Difference-based semiparametric estimation of
> partial linear regression models", The Stata Journal, 6(3): 377--383.
> http://www.stata-journal.com/article.html?article=st0109
>
> -----------------------------------------
> Maarten L. Buis
> Department of Social Research Methodology
> Vrije Universiteit Amsterdam
> Boelelaan 1081
> 1081 HV Amsterdam
> The Netherlands
>
> visiting address:
> Buitenveldertselaan 3 (Metropolitan), room Z434
>
> +31 20 5986715
>
> http://home.fsw.vu.nl/m.buis/
> -----------------------------------------
>
>
> __________________________________________________________
> Sent from Yahoo! Mail.
> A Smarter Email http://uk.docs.yahoo.com/nowyoucan.html
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
>
>
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
__________________________________________________________
Sent from Yahoo! Mail.
A Smarter Email http://uk.docs.yahoo.com/nowyoucan.html
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
