This pull request implements an improved version of the general loglikelihood evaluation, i.e. the loglikelihood evaluation when there is no structure in the covariance matrix that we can take advantage of. The direct inversion of the covariance matrix is replaced by a Cholesky factorization approach, which offers the following advantages:
This pull request implements an improved version of the general loglikelihood evaluation, i.e. the loglikelihood evaluation when there is no structure in the covariance matrix that we can take advantage of. The direct inversion of the covariance matrix is replaced by a Cholesky factorization approach, which offers the following advantages: