Thank you in advance for any comments. I have been searching futilely
all day in Stata documentation, online articles, etc. for the answer to
what I initially thought would be a simple question:
Winship and Radbill noted back in the 90's that applying sampling
weights to regression analysis can result in standard error estimates
that are compromised. Is this because at the time they were writing,
most software packages treated the weights as frequency weights and
consequently inflated the sample size? Given the advances made in STATA
8, if I were to
.regress Y X1 X2.Xn [pweight=weight]
would my standard error estimates be compromised as Winship and Radbill
noted back then, or does pweight now correct for any problems with these
estimates brought about by the act of weighting?
I have seen some threads similar to this in the Stata list archives, but
I was not able to determine the answer to the above question based on my
reading of the threads.
Also, can anyone point me to any documentation as to exactly what/how
pweights are applies. For example, I know that fweights are analogous
to running an unweighted regression on a dataset that has the correct
number of observation replications denoted by the fweight. However, I
don't have a concept in my head of how pweights are actually
applied...that is, can anyone briefly state a conceptualization such as
the one I made above about pweights, or does anyone have access to
technicalities/formulas about how pweights are applied?
Again, thanks!
Barbara Hamilton
Center for Labor Market Studies
Northeastern University
*
* 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/
