Re: st: Controls for Lowess smoothing

[jean ries <jean.ries@gmail.com>]

> Date: Sun, 18 Dec 2005 11:39:29 -0500
> From: Tinna <statalist@gmail.com>
> Subject: st: Controls for Lowess smoothing
>
> Dear Statalisters,
>
> Is it possible to use control variables in a locally smoothed
> (nonparametric) regression?
>
> Tinna
>
> P.S. my command looks like this.
> lowess healthdummy lowessequiv1000, bwidth(0.6) ytitle(Probability of
> Being in Good Health) xtitle(Income (Simulated and Adjusted for Family
> Size)) title(Lowess Smoothed Regression of Income on Probabiltiy of
> Good Health) by(male)
Tinna,

You could use "partial linear models" (Yatchew 1997). I don't know if 
there is some Stata code out there that implements these methods. On the 
other hand, these methods are not very difficult to implement either.  
If you are curious and want to see some applications, or if you want to 
learn about extensions, you can as well have a look at a survey article 
(Yatchew 1998) and/or a textbook (Yatchew 2003) by the same author.

Yatchew, A., 1997, An Elementary Estimator of the Partial Linear Model, 
Economics Letters,  57, 135-43
Yatchew, A., 1998, Nonparametric Regression Techniques in Economics, 
Journal of Economic Literature, 36, 669-721.
Yatchew, A., 2003, Semiparametric Regression for the Applied 
Econometrician, Cambridge University Press.

Hope this helps,

jean
*
*   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/