I build a PC-Kriging and calculate the covariance matrix of outputs of Monte-Carlo samples using uq_evalModel. But sometimes, the obtained covariance matrix may be not symmetric or positive definite.
Why? How can I solve this problem?
I build a PC-Kriging and calculate the covariance matrix of outputs of Monte-Carlo samples using uq_evalModel. But sometimes, the obtained covariance matrix may be not symmetric or positive definite.
Why? How can I solve this problem?