Norbert Michel wrote:
> When using the survey command svymean, what, exactly, is the
> interpretation of the design effect "deff" in the output?
Check out
http://www.ats.ucla.edu/stat/stata/seminars/svy_stata_intro/default.htm
for more on this and other fruit fancies about doing -svy:- analysis in
Stata. You have to scroll down a bit to learn about -deff-, but you've got
_lots_ of useful material to go with it, and two neat movies to watch as
well!
> Also, if I want to run a difference in means test (using survey data),
> do I have to do this manually?
Looking at the options covered by -whelp survey-, that looks tough to do
if you're looking to get output test statistics. The closest I can get you
there is
. svy: mean x, over(y)
assuming that -x- is continuous and -y- is categorical. But it doesn't
give t-test-style statistics along with this. Maybe this is correct or
maybe it's an oversight: hard to say.
Perhaps other listees can help you out on this point.
Hope this helps.
CLIVE NICHOLAS |t: 0(044)7903 397793
Politics |e: [email protected]
Newcastle University |http://www.ncl.ac.uk/geps
Whereever you go and whatever you do, just remember this. No matter how
many like you, admire you, love you or adore you, the number of people
turning up to your funeral will be largely determined by local weather
conditions.
*
* 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/
