R help

Here is a solution, but it may take several seconds to run.

x <- matrix(rnorm(1050*1000),1050,1000)
mat <- t(x)%*%x

This is the idea behind Wishart random matrices. In theory, that matrix 
should be positive definite. This can be verified with

eigen(mat,only.values=T)

Also read ?ninvwish in package "norm". But I am not sure if it was 
designed for large matrices.

HTH,
Jerome

 Dear friends,
 How can I generate (simulate) a large, say 1000x1000, positive definite
var-covar matrix?

 Regards,

 Max




---------------------------------


	[[alternate HTML version deleted]]

______________________________________________
R-help at stat.math.ethz.ch mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help