Correlation matrix

Bomba · February 25th, 2003, 1:31 pm

Anyone knows a method to apply perturbations to a correlation matrix, preserving the positive definiteness of the matrix and hopefully very low time consuming ? Thanks

Nonius · February 25th, 2003, 3:38 pm

send me a PM.

tubul · February 26th, 2003, 2:47 am

There was a paper on this in the RiskMetrics Monitor (1997, 4th Quarter). Here it is:Regards,Tubul

tubul · February 26th, 2003, 2:48 am

Sorry about that. I think I got it this time.Regards,Tubul

Silvershark · February 26th, 2003, 7:05 am

Bomba,Have a look at Peter Jäckel's book "Monte carlo methods in finance". Theres a chapter devoted to the subject.Regards,

Bomba · February 26th, 2003, 3:18 pm

Well , thank you all.