[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: svyintreg vs. intreg with pweights
I have survey data on incomes (in brackets) and pweights are provided as
I would like to find the average income. To do this, I regress the interval
ends on a constant using -intreg-
This command works:
intreg inc1 inc2 [pw=my_weight_variable]
This syntax does not work:
svyintreg inc1 inc2
(fails after -svyintreg- with the error message "initial values invalid").
There are no zero or missing weights (if it is of any importance).
My questions are:
1) are the above two syntaxes equivalent?
2) if the answer to #1 is negative, then what is the rationale behind
choosing one vs the other?
3) how can I specify that -svyintreg- takes the estimates from
unweighted -intreg- as initial values?
Or more generally, how to make the svy version to work in my case?
* For searches and help try: