Peter Dalgaard <p.dalgaard <at> biostat.ku.dk> writes: > No, he wants to compare two correlation coefficients, not test that > one is zero. That's usually a misguided question, but if need be, the > Fisher z transform atanh(r) can be used to convert r to an > approximately normal variate with a known variance 1/(N-3) and > comparing r1 and r2 from two independent samples is straightforward. > The correlated case (like cor(x,y) vs cor(x,z)) is more complicated.
It seem the more complicated case is often of more substantive interest in many settings: is children's income more strongly correlated with parent's education than parent's income? ______________________________________________ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
