# Re: st: weigths

 From "Anthony Gichangi" <[email protected]> To <[email protected]> Subject Re: st: weigths Date Sun, 1 Aug 2004 11:50:01 +0200

```hi Antonio
The square root will automatically be taken when you specify
regress y x1 x2 x3 [aweight=pop]  see Techinical note on
Weighted regression page 343 N-R manual. So if you specify
gen wt=sqrt(pop)
regress y x1 x2 x3 [aweight=wt]
you will be doing this twice. I guess you don't want to do that..

Regards
Anthony

----- Original Message -----
From: "Antonio Rodrigues Andres" <[email protected]>
To: <[email protected]>
Sent: Tuesday, August 03, 2004 11:04 AM
Subject: Re: st: weigths

> i think that it is correct to use
>
> gen wt=sqrt(pop)
> regress y x1 x2 x3 [aweigth=wt]
>
>
> >>> [email protected] 08/03/04 10:41AM >>>
> My
>  dependent variable is the mortality rate. Since the variance of
> ln(d/p)
>  is inversely proportional to p (population), this implies
> heteroskedasticity. To correct for it, observations should be weighted
>
> by the square root of the denominator of the mortality rate, i.e.,
>  population. In Stata,   i am using
>
>  xi: regress y x1 x2 i.country i.year [w=1/pop],
>  Is that correct? I might also use the robust option
>  I would appreciate any answers
> > Antonio
>
> *
> *   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/
*
*   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/
```