[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: conformability error for logit model of subpopulation
This seems to have come up in April 2006, but I cannot find a resolution in
the archives. The author indicated that inteff does not work with svy data.
At the same time, Stata Tech Support kindly confirmed the syntax but I
repeatedly get a conformability error r(503) for subsamples of the
population (inteff works for the full sample):
svy: logit HSdip Fpov90 gender3 povgen IV1...IVn if white==1
svy, subpop(white==1): logit HSdip Fpov90 gender3 povgen IV1...IVn *and
then, following either of the previous logit models: inteff HSdip Fpov90
gender3 povgen IV1...IVn if white==1
Various efforts (ignoring survey design, per author's guidance; changing
subsample; forcing Stata version 8.2, per an archived suggestion) have not
removed the problem. I consistently can only run inteff after a logit model
of the full sample.
Any ideas would be much appreciated.
* For searches and help try: