> I presume that you want the density of a multivar normal distrib. You > don't calculate the inverse; you just need the quadratic form. I think > that Searle's matrix algebra book gives the computations. off hand, for > the quad form x'A-1x I'd get the cholesky factor of A = LL' and solve > for z in Lz = x and then z'z is the quad form. Perfect! Thanks a lot -- ==================================== Gökhan BakIr Insitute of Robotics and Mechatronics German National Research Institute for Aero and Space 82234 Oberpfaffenhofen Tel: + 49-8153 - 28 2440 ICQ : 82040497 www.fastray.de ================================================================= Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =================================================================