--- Tam Lin <[email protected]> wrote:
> I am using survey data with probability weights. I want to see if
> there is a significant difference in age (continuous variable) across
> nine different ethnic groups (categorical variable). A one-way ANOVA
> would seem to be the appropriate test here.
>
> However, STATA 9 is too clever for me and gives me an error message
> when I try to run a one-way ANOVA with pweight.
>
> Here is the syntax if it helps to clarify:
>
> oneway rage ethnicity4 if subpop6==1 [pweight=wtfinds], tabulate
> scheffe
>
> (my subpopulation is restricting this test to only those aged 55 or
> over)
>
> My question is, why is there an error and is there a way to run this
> test with pweights?
It looks like you have a complex survey design, see -help svy-, in
which case you should use the subpop option within the
-svy- prefix. Anyhow -oneway- is not svy capable. This is not a bad
thing as ANOVA is nothing else than a weird way of doing
-regress-. If I interpret your situation correctly then the following
should give you the correct test:
svyset [pweight=wtfinds]
xi: svy, subpop(subpop6): regress rage i.ethnicity4
testparm _I*
Hope this helps,
Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
