Re: st: glm with aweight

["David W. Harless" <dwharles@vcu.edu>]

Sergio Goldbaum wrote:
> Dear Statalisters:
>
> This is probably a very simple question, so I apologize myself in advance.
> Following Berndt "The Practice of Econometrics", chapter 7, exercise 3 (pg.=
>  341), I have run:
>
> glm y x1 x2 x3 [aweight =3D x4]
>
> and Stata gave me the expected coefficients and std deviation (the ones sho=
> wn in the textbook).
>
> Then, I tried to use a "brute force" data transformation approach, that is,=
>  to transform the variables by myself and run an OLS
>
> regress y x1 x2 x3
>
> However, I could not get the same glm results. So, my question is: How exac=
> tly "aweight" transforms variables?
Serigio,
To do the WLS estimation by hand, you must transform the constant too, include the 
transformed constant explicitly, and use the -noconstant- option.  See the FAQ at
http://www.stata.com/support/faqs/stat/crc36.html.

I hope this helps,
Dave Harless

*
*   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/