Richard Williams replied to Anuja Saurkar
> >3) I am using weights:
> >so generally I write
> >
> >tabstat variable [aweight=weight] by variable....
> >
> >Is there any way I can use weights without including
> >it in the tabstat command? I want to run a bunch of
> >summary table, would like to use weights for all of
> >them.
>
> I suspect not, but I am curious too. A difference that
> strikes me between
> SPSS and Stata is that, in SPSS, I can specify weights or
> filters (i.e.
> temporary sample selections) and they continue to hold until
> I tell SPSS
> otherwise; in Stata I have to keep on specifying the weights
> or filters
> with every command.
I think Richard is right. There is no way of setting analytic
weights. (In a separate posting Rafa De Hoyos mentions setting
survey weights, which does not seem to apply to this problem.)
The design issue is straightforward, a trade-off between
setting things until they're changed, and thus saving on
typing, and of overlooking what you've set. Stata lets
you set various things, but not analytic weights.
Historically, one good reason for that was that typing
the same stuff is usually easy with facilities like PageUp.
Another is that long weight specification can be saved
in local macros
local myw "[aw=verylongvariablename]"
tabstat variable `myw'
More recently, -foreach- makes it a lot easier
to cycle round almost similar stuff
foreach v of var <varlist> {
tabstat `v' [aw=weight] , by(<whatever>)
}
and I guess wildly that may be the most practical
answer to Anuja's problem, which appears to be
wanting to cut down on typing.
Nick
[email protected]
*
* 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/
