Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: RE: differential classification table with multiple variables


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: RE: differential classification table with multiple variables
Date   Wed, 2 Apr 2008 17:06:23 +0100

Not clear what you want precisely here, but -groups- may help. 

See 

SJ-3-4  pr0011  . . . . . . . .  Speaking Stata: Problems with tables,
Part II

See .pdf copy at at
http://www.stata-journal.com/sjpdf.html?articlenum=pr0011

Nick
n.j.cox@durham.ac.uk 

Pruitt, Sandi L

I have multiple (n=15) categorical variables (in quartiles) that I think
represent different aspects of the same construct. I am interested in
putting together a differential classification table to explore whether
these variables actually classify people into different groups.  
 
I don't have any theoretical reason with which to select a smaller
subset of measures and I don't yet want to do a principal components
analysis. I've also already looked at correlations between these
variables. Basically, I'm looking for some way that I can perform an
"ocular test"--to see for myself how people are classified into these
groups.
 
I have two questions: 
1. Is there a simple program or code I can use to make such a table or
otherwise display this data?  (I tried bigtab but it only allows for
inclusion of 3 variables.)
2. Or, alternatively, is there another method which which to explore the
possibility of differnetial classification?

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index