Dear R-helpers, In a data set I got from a medical doctor there are six treatment groups and (about) 5 bivariate responses in each group. Using 'manova', it is easy to see significant differences in treatment effects, but the doctor is more interested in the correlation between the two responses (within groups). I'm willing to assume a common value over groups, and one way of estimating and testing the common correlation would be to use 'cor.test' on the residuals from 'manova', but I guess that the resulting p-value (from testing zero correlation) will be far too optimistic (it is in fact 4.5e-5).
What is the 'right' way of doing this in R? -- G�ran Brostr�m tel: +46 90 786 5223 Department of Statistics fax: +46 90 786 6614 Ume� University http://www.stat.umu.se/egna/gb/ SE-90187 Ume�, Sweden e-mail: [EMAIL PROTECTED] ______________________________________________ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
