Computes an unbiased estimate a variance-covariance matrix.
The variance-covariance matrix is computed as an unbiased estimator of
the population variance-covariance. It is computed as the moment matrix
of deviations about the mean divided by the number of observations minus
one, \(N - 1\). For an observed variance-covariance matrix which uses \(N\)
rather than \(N - 1\) see