Ref. dynare#1673

Ref. dynare#1673

Ref. dynare#1673

Ref. dynare#1673

Ref. dynare#1673

Ref. dynare#1673

 - Rewrote doc headers
 - Changed function signatures
 - Removed persistent variables
 - Compute the mode of the particle weights
 - Return the covariance matrix of the particles in the last period
 - Various cosmetic changes

include parallelisation, correction of the likelihood calculation for the Amisano and Tristani option and the possibility of monte carlo draws for the proposal.

Properly terminate nonlinear_kalman_filter if non-positive definite m…

Otherwise, crashes can happen during mode-finding

Make the distinction between original Amisano and Tristani's way to calculate particles weights and the likelihood (CPF1) and Murray's way (CPF2).