Tests of correlations are notoriously sensitive to the normality
assumption. So any solutions may be subject to that problem. One
approach might be to use the Fisher z transformation for the
correlations and then test to see if each is 0 or not. I'd be cautious
about any p-value citations.
To compare correlation A1 with A10 you would use z(A1)-z(A10) and go
from there.
Tony
Peter A. Lachenbruch
Department of Public Health
Oregon State University
Corvallis, OR 97330
Phone: 541-737-3832
FAX: 541-737-4001
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of
[email protected]
Sent: Monday, June 16, 2008 1:37 AM
To: [email protected]
Subject: st: can I compare correlations with t-tests (Bonferroni)?
I have item A in a scale "interest in participating to their countrys or
to their regions economic and technological development", which I want
to compare with 12 items in another scale.
I would like to show that:
- item A is correlated with 10th, 11th and 12th item in the other scale
- such correlation is "stronger" than between A and 1st item, A and 2nd,
.... A and 9th
This is obvious on the correlation table since correlation between A and
other items are:
0.1095 (A and 1st) 0.1227 (A and 2nd) 0.1285 0.1833 0.1487 0.1546 0.1483
0.2489 0.278 0.2037 (A and 12th)
Is there a way/a test in Stata to say it statistically (i.e. with some
p-value)?
Many thanks in advance for your help,
Nicola
P.S. From statalist-digest V4 #3088 on, I noticed that the characters'
size has been reduced (from medium to small, according to Eudora's
version 7 standards). Is it true or did I incidentally changed some
setting on my pc?
*
* 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/
*
* 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/
