Re: Correlation matrix of regression coefficients - Cox regression analysis

Posted by Marta García-Granero on Sep 18, 2006; 5:52pm
URL: http://spssx-discussion.165.s1.nabble.com/Re-Interesting-links-in-my-opinion-tp1070904p1070908.html

Hi Christian

The correlation matrix you mention is used only to estimate CI for HR for
individuals/groups with certain covariate patterns, I think it is not very
useful to know whether they are significant or not. As a matter of
fact, you must use CONVERT to turn it into a Variances/covariances
matrix (the one you really use for CI estimation).

What on earth do you need those p-values for? ;)

CB> Using Cox regression analysis, I'd like to estimate the p-value for each
CB> correlation reported on the correlation matrix of regression coefficients.


--
Regards,
Dr. Marta García-Granero,PhD           mailto:[hidden email]
Statistician

---
"It is unwise to use a statistical procedure whose use one does
not understand. SPSS syntax guide cannot supply this knowledge, and it
is certainly no substitute for the basic understanding of statistics
and statistical thinking that is essential for the wise choice of
methods and the correct interpretation of their results".

(Adapted from WinPepi manual - I'm sure Joe Abrahmson will not mind)