stepan@cepremap.org (Stephane Adjemian) writes:

commit 894b3d69f4662a1132c0f7fb50083bf982745536 Author: Stéphane Adjemian (Charybdis) stephane.adjemian@univ-lemans.fr Date: Thu Sep 27 14:47:21 2012 +0200

Added an option to decide if dsge_likelihood should call univariate filters when the covariance matrix of
the prediction error is singular (default is yes).

Should we add an interface and documentation for that option?