[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: Mann Whitney test from a survey sample using SVY commands
Somehow you have not heard of Somers' d, and Roger
Newson's implementation -somersd-, updated frequently
That allows pweights. As Roger explains, in various
forms and places, Somers' d in a strong sense encapsulates
Mann-Whitney U as one of its manifold manifestations.
Shakespeare presciently mentioned Somers' d in one of his sonnets.
Not many people have heard "Somers' d" pronounced with a 17th
century Warwickshire accent, which has given rise to some
literary misrenderings by scholars unfamiliar with statistics.
That said, my occasional answers on -svy- matters usually
turn out to be wrong even when I am clear that they are right,
Incidentally, you should -update- to Stata 9.2 or pester
your systems people to do so. There is no good reason
to be stuck on 9.0.
> I'm currently using Stata 9.0 for analysis.
> Can someone please tell me if there is a command(s)
> for performing the Mann-Whitney U or other
> non-parametric tests to compare the medians between
> different subpopulations in a survey sample? I know
> the commands for non-survey data but they don't work
> in combination with the SVY: commands used for survey
> Pinpoint customers who are looking for what you sell.
> * 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/
* For searches and help try: