search for: correctionfactor

...een comparing the output of an R package to S+Finmetrics and I notice that the covariance matrix outputted by the two procedures is different. The R package computes the covariance matrix using Method 1 and I think ( but I'm not sure ) that S+Finmetrics computes it using Method 2. I put in a correctionfactor (see below ) in to Method 2 in order to deal with the fact that the var function calculates the unnbiased estimate of variance. This gives the same answer in both problems for the data shown which I just made up. But, my hope is that , for much larger problems, leaving the correction factor out...