Given a crosstabulation between two variables with same number of
categories, is is possible to structure an analysis using spss that tests
whether the numbers in corresponding upper and lower diagonal cells are not
different?
I can get an overall test with a chi square but I'd like to break that down
and test comparisons between specific corresponding cells. I kind of thin I
remember seeing a discussion of models like this in Agresti but I have never
tried to do one before and am not sure which procedure to use and how to set
it up--assuming it can be done in spss, which I'll bet it can.
Thanks, Gene Maguin
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Locked
