I have as dependent variable the death rate. As I get
heteroskedasticity, to compensate for it observations should be weigthed
for the square root of the denominator of the death rate (i.e
population). First, I am not sure if this specification is correct with
analytical weights
regress y x1 x2 x3 [w=1/pop]
Stata does x1/sqrt(pop) is that correct?
thanks
*
* 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/
