On 8 Jun 2000 01:01:18 GMT, <[EMAIL PROTECTED]> wrote:
> If the following factorial survey was performed:
> 192 dimensions with 200 respondents answering 10 vignettes each.
> So, each vignette would have about 10 responses.
>
> The problem is that the dimensions were not randomized on the vignettes.
> If there were correlations between some of the dimensions, then
> one could use "blocking" and combine some of them?
>
> Would this then be a problem for an expert statistician? Is this also a
> situation that econometricians often encounter, dependence(?) or
> correlations between the independent variables?
It sounds like coverage is a little thin, and your estimation between
particular Dimensions might be a problem. But the problem is
"unbalanced blocks" and you should be able to get estimates, even if
they aren't very good ones.
For a 200x200 problem you might want to try a shortcut like this:
Create a variable that has 200 Means, one for each ID, and then use
that variable as a covariate for an ANOVA by 192 dimensions; that
gives you Adjusted means for vignettes. [The DF for the test should
be re-computed, subtracting 200, if you want to test those means.]
Similarly create a variable that has 192 means, one for each vignette,
and use that as covariate for ANOVA by 200 IDs, if you want those as
adjusted means.
I don't know what econometricians encounter.
--
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
===========================================================================
This list is open to everyone. Occasionally, less thoughtful
people send inappropriate messages. Please DO NOT COMPLAIN TO
THE POSTMASTER about these messages because the postmaster has no
way of controlling them, and excessive complaints will result in
termination of the list.
For information about this list, including information about the
problem of inappropriate messages and information about how to
unsubscribe, please see the web page at
http://jse.stat.ncsu.edu/
===========================================================================
