Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Nick Cox" <n.j.cox@durham.ac.uk> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | st: RE: Correlating a variable against itself over two time moments |
Date | Fri, 6 Aug 2010 15:35:13 +0100 |
You should -reshape wide- using identifier and dummy as jointly defining observations in a wide structure. Then use -correlate-. Nick n.j.cox@durham.ac.uk Martin Pszczola I have a data set that has 51 Likert Scale variables and a dummy variable for pretest/posttest. I am trying to obtain a correlation matrix in Stata for the correlations of the variables against themselves over the two time moments. For example, say I have variable P1. I want to correlate P1 from the pretest against P1 from the posttest. If anyone could provide advice on how to go about doing this in STATA, I would appreciate it. * * 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/