I am trying to estimate a relatively large model with unit roots, deterministic trends and measurement error. The code works fine in Dynare 3. In Dynare 4, I get instead the following error message
??? Error using ==> DiffuseLikelihoodH3_Z
Too many input arguments.
Error in ==> DsgeLikelihood at 288
LIK = DiffuseLikelihoodH3_Z(ST,Z,R1,Q,H,Pinf,Pstar,data1,trend,start);
Looking at the syntax of this function, there seems to be an inconsistency between the syntax of the function is DsgeLikelihood and the syntax in DiffuseLikelihoodH3_Z, but I am not sure how to fix the problem. Is this a known problem? It seems to me that it happens when there are less shocks than observables, even if measurement errors make up for the difference
By the way, even after going around that problem, I still seem to have problems with DiffuseKalmanSmootherH3_Z…