As you say, non-integers cannot be frequency weights.
Otherwise how these weights are to be interpreted looks like
a substantive matter. You need to move upstream
towards the author or supplier of the dataset.
Nick
[email protected]
Lijun Song
> I come to another questions. In the original spss data, there
> are three
> kinds of weights. One is gender weights, oen is rural-urban
> weights,and
> another is the combination of gender and rural-urban weights. What is
> the application difference between these three weights?
>
> I am not familiar with the spss data. So I am also confused regarding
> what should I use in stata. The outputs have shown that the
> weights are
> noninteger, so that I could not use fw. Then between aw and pw, which
> one should I use?
*
* 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/
