Example of estimation working in 4.0.0 but not 4.0.3

[doctorwes]

I am trying to estimate a simple model. Estimation runs successfully in 4.0.0, but 4.0.3 gives me the attached error message. What would have changed between versions? I've attached the .mod file and the data file. Thank you in advance if you can help!

Code: Select all

??? Error using ==> chol
Matrix must be positive definite.

Error in ==> metropolis_hastings_initialization at 52
d = chol(vv);

Error in ==> random_walk_metropolis_hastings at 43
[ ix2, ilogpo2, ModelName, MhDirectoryName, fblck, fline, npar, nblck, nruns, NewFile, MAX_nruns, d ] = ...

Error in ==> dynare_estimation_1 at 940
        feval(options_.posterior_sampling_method,'DsgeLikelihood',options_.proposal_distribution,xparam1,invhess,bounds,gend,data);

Error in ==> dynare_estimation at 62
    dynare_estimation_1(var_list,varargin{:});

Error in ==> zero_bound at 206
dynare_estimation(var_list_);

Error in ==> dynare at 102
evalin('base',fname) ;


[MichelJuillard]

Version 4.0.3 is more discriminant with problems in the Hessian matrix before doing Metropolis. Try to use mode_compute=6. It takes much longer, but will deliver a positive definite covariance matrix that will allow you to continue with metropolis

Best

Michel

[doctorwes]

Thank you! This seems to work perfectly. I was not aware of mode_compute=6, but I now see it was added by Stephane some time ago. I will use it in the future (and perhaps request a faster computer).