Hello, I would greatly appreciate having some feedback on a problem. My data consist of two matrices of robust rank correlations between data collected in different conditions. The two matrices represent data from two between-subjects conditions. Each of the matrices correlates data from each of four within-subjects conditions, given by the factorial combination of two within-subjects factors. I would like to test the significance of the effects of my experimental factors, and of their two- and three-way interactions on the observed correlations. Now, am I missing some basics of multivariate statistics or I should seriously consider structural equations modeling, which seems an overkill for my problem? Thank you very much, Bruno ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Bruno L. Giordano, Ph.D. Music Perception and Cognition Laboratory CIRMMT http://www.cirmmt.mcgill.ca/ Schulich School of Music, McGill University 555 Sherbrooke Street West Montr?al, QC H3A 1E3 Canada