st: St: glogit

["Cavallo, Alexander" <acavallo@lexecon.com>]

Title: St: glogit

I am estimating a glogit model explaining the percent female in occupations.  I have aggregated my data (both dependent and independent variables) using pweights.  Because of this, percent female does not equal # females/total # in occupation, but rather sum(female wgts)/sum(all wgts in occupation).  My concern is in getting the weights right for WLS.  The manual states that the weight for each cell is proportional to 1/(nj*pj*(1-pj)) where nj is the number of observations for the cell and pj is the predicted probability.  If I use the unweighted counts for the analysis, then I get the dependent variable wrong with the "correct" number of obs for variance calculation.  If I use the weigthed counts, then I have the right dependent variable but nj is about 500 times too big (the average weight is 500).

Here's my idea on solving this:

Create new count variable:
        newfemales=wgtfempct * nobs
        glogit newfemales nobs x1 x2 etc
where   wgtfempct is the weighted % female
        nobs is the unweighted # of obs in occ

Is anyone aware of a literature on this?  Any comment would be appreciated.

--Alex Cavallo
Lexecon, Inc.
332 South Michigan Avenue
Suite 1300
Chicago, IL 60604
(312) 322-0208 voice
(312) 322-0218 fax