Or if you have zero, missing, or negative values in the old weight
variable, you might want to:
. gen double newwt=round(oldwt,1)
. drop if newwt<=0 | newwt>=.
. expand newwt
. locpoly yvar xvar
On 8/8/05, austin nichols <[email protected]> wrote:
> There is probably a good reason the command cannot
> be used with weights. N.B. "cannot take weights" means
> it can't take weights (no puede lo usar) and "can not take
> weights" means it can be run without weights (puede no
> lo usar). I apologize if the translation makes no sense.
>
> If you expand data to cheat the command, you will
> get incorrect results (notably, the std errors will be
> WAY off if you've got, say, pweights).
>
> That said, you can just
> . gen double newwt=round(oldwt,1)
> . expand newwt
> . locpoly yvar xvar
> if you want to run a weighted locpoly, for example.
>
> -----Original Message-----
> From: Luciana Sampaio Alves [mailto:[email protected]]
> Sent: Monday, August 08, 2005 2:15 PM
> To: [email protected]
> Subject: Re: st: Re:
>
> I want to use a command that can not be used along with weghts.
> Do you know how to expand the base?
>
> *
> * 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/
