As Nick already noted, this is usually done with Fisher's z because the sampling distribution of the correlation coefficient itelf is decidedly unpleasant when correlations are different than 0 (it is not pivotal if I recall right, and is notably skewed). Fisher's z is just arctanh and the asymptotic SE of a Fisher's z transform is 1/sqrt(n-3).
James Steiger (Psychology, Vanderbilt) wrote a primer on comparing correlation coefficients. See his web page. The most recent version of the article I know of is:
J. Steiger (2004). Comparing correlations. In A. Maydeu-Olivares and J.J. McArdle (eds.). Contempoary Psychometrics: A Fetschrift in Honor of Roderick P. McDonald. Mahwah, NJ: LEA.
-----Original Message-----
From: [email protected]
To: "[email protected]" <[email protected]>
Sent: 3/10/2009 3:35 AM
Subject: st: corcor
Are there any functions like corcor (H0: cor(x1x2)=cor(x1x3)) that test
cor(x1x2)=cor(x3x4)?
Thank you.
*
* 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/
*
* 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/
