[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: RE: Using weights with tabulate command
At 04:11 PM 3/18/2004 +0000, Nick Cox wrote:
Also, for the purposes of the tab command, he might want [iw=weight01]. It
depends on what the goal is. This would give you the estimated number of
households in each country that have a particular characteristic, e.g.
there are are an estimated 400,000 people in the UK with illness 1. You
might get Ns in the millions, even though the sample is only a few
thousand. With aweights, the weights will be rescaled to reflect the
sample Ns. -help weights- provides more info, even better is section 23.16
of the User's Guide. Stata's weighting options are more extensive than
what I was used to so reading through that section was very helpful to me.
With -tabulate-, weights are assumed to be frequency
weights unless otherwise indicated. Your weights
sound like analytic weights.
. by country: tab illness [aw=weight01]
With -summarize- weights are assumed to be analytic
weights unless otherwise indicated.
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
* For searches and help try: