this may be a very basic question.
I have the mean and variance for 12 lognormal distributions:
location 0.90109 0.59587 0.80460 0.65178 0.76307 0.52575 0.41322 0.30059
scale 0.63551 0.65525 0.64227 0.65198 0.64503 0.65915 0.66496 0.67022
How can I determine the covariance matrix from this data which I can plugin into the code given below.
Basically, I am trying to create a sum of these distributions using the Fenton Wilkinson approximation.
Matlab code: http://www.snowelm.com/~t/doc/tips/20110902.en.html#fw
Actual paper: http://www.ee.oulu.fi/~pekkap/finsig03_pp.pdf
Any explanation is very appreciated.