June 2012 - Dev - dynare.org

[Trac] #164: consider using bvar provided by Zha and Waggoner instead of our own
by Trac Dynare 05 Jun '12

05 Jun '12

#164: consider using bvar provided by Zha and Waggoner instead of our own --------------------------+------------------------------------------------- Reporter: houtanb | Owner: Type: feature | Status: new Priority: major | Milestone: 4.3 Component: Core M-files | Version: Keywords: | --------------------------+------------------------------------------------- Their code provides a superset of ours. -- Ticket URL: <https://www.dynare.org/trac/ticket/164> Dynare <http://www.dynare.org> The Dynare project

1 2

[Trac] #184: Auxiliary variables for leads.
by Trac Dynare 05 Jun '12

05 Jun '12

#184: Auxiliary variables for leads. --------------------------+------------------------------------------------- Reporter: stepan | Owner: houtanb Type: enhancement | Status: new Priority: major | Milestone: 4.3 Component: Preprocessor | Version: Keywords: | --------------------------+------------------------------------------------- The last loop in add_auxiliary_variables is highly inefficient. The the residuals of the static model are evaluated (many times) to compute the the steady state levels of the auxiliary variables. But in the preprocessing stage, the expressions of the auxiliary variables (in terms of the endogenous variables) are known. The preprocessor should write a routine defining the auxiliary variables as a function of the endogenous variables. Depending on the current options, this routine may be a matlab function, a mex or bytecode. With such a function we won't need to infer the steady state of the auxiliaries from the residuals of the static model... -- Ticket URL: <https://www.dynare.org/trac/ticket/184> Dynare <http://www.dynare.org> The Dynare project

1 2

[Trac] #181: Display a summary of warnings at the end of Dynare run
by Trac Dynare 05 Jun '12

05 Jun '12

#181: Display a summary of warnings at the end of Dynare run --------------------------+------------------------------------------------- Reporter: sebastien | Owner: Type: feature | Status: new Priority: minor | Milestone: 4.3 Component: Core M-files | Version: Keywords: | --------------------------+------------------------------------------------- At the end of a run, display a message if a warning was emitted (either by the preprocessor, or by MATLAB/Octave code). Some harmless warnings should probably be filtered out. -- Ticket URL: <https://www.dynare.org/trac/ticket/181> Dynare <http://www.dynare.org> The Dynare project

1 3

[Trac] #229: update markov_switching statement
by Trac Dynare 05 Jun '12

05 Jun '12

#229: update markov_switching statement ------------------------------------+--------------------------------------- Reporter: houtanb | Owner: houtanb Type: feature | Status: new Priority: major | Milestone: 4.3 Component: Markov-Switching SBVAR | Version: Keywords: | ------------------------------------+--------------------------------------- * remove the regime option * replace number_of_states with number_of_regimes * add restrictions option * allow duration to accept a vector of length number_of_regimes * remove the passing of INF_CONSTANT to duration See http://www.dynare.org/DynareWiki/MarkovSwitchingInterface -- Ticket URL: <https://www.dynare.org/trac/ticket/229> Dynare <http://www.dynare.org> The Dynare project

1 4

[Trac] #172: improve derivation engine for derivatives of STEADY_STATE wrt parameters
by Trac Dynare 05 Jun '12

05 Jun '12

#172: improve derivation engine for derivatives of STEADY_STATE wrt parameters --------------------------+------------------------------------------------- Reporter: sebastien | Owner: sebastien Type: enhancement | Status: new Priority: major | Milestone: 4.3 Component: Preprocessor | Version: Keywords: | --------------------------+------------------------------------------------- Currently the derivatives of STEADY_STATE operator wrt to parameters are not handled in an efficient way, because the preprocessor does not exploit the a priori information for identifying null derivatives. This results in huge files for not so complicated models, which cannot be exploited by identification routines. The proposal is to implement an algorithm in the preprocessor for identifying null derivatives ex ante: - Create a non-directed graph whose nodes are the endogenous variables and the parameters - For each pair of nodes, add an edge between the two if there is an equation in the static model containing both corresponding symbols (endogenous/parameters) - For each endogenous, its derivative wrt a parameter is always zero if there is no path between the node representing the endogenous and the node representing the parameter. -- Ticket URL: <https://www.dynare.org/trac/ticket/172> Dynare <http://www.dynare.org> The Dynare project

1 6

[Trac] #116: IRF: give the possibility to choose the starting point (at least at order 2 and above)
by Trac Dynare 05 Jun '12

05 Jun '12

#116: IRF: give the possibility to choose the starting point (at least at order 2 and above) --------------------------+------------------------------------------------- Reporter: sebastien | Owner: Type: feature | Status: new Priority: major | Milestone: 4.2 Component: Core M-files | Version: Keywords: | --------------------------+------------------------------------------------- In particular, give the possibility to start from the stochastic steady state -- Ticket URL: <https://www.dynare.org/trac/ticket/116> Dynare <http://www.dynare.org> The Dynare project

1 4

[Trac] #115: IRF: add the possibility to change the size of the shocks in the computations
by Trac Dynare 05 Jun '12

05 Jun '12

#115: IRF: add the possibility to change the size of the shocks in the computations --------------------------+------------------------------------------------- Reporter: sebastien | Owner: Type: feature | Status: new Priority: major | Milestone: 4.2 Component: Core M-files | Version: Keywords: | --------------------------+------------------------------------------------- At order 1, it is equivalent to changing the standard deviation of the shocks and adding the corresponding inverse transformation in the equations. But at orders 2 and above, the equivalence does not hold. -- Ticket URL: <https://www.dynare.org/trac/ticket/115> Dynare <http://www.dynare.org> The Dynare project

1 3

Status of testsuite in master branch
by Sébastien Villemot 05 Jun '12

05 Jun '12

*************************************** * DYNARE TEST RESULTS * * for make check-matlab * *************************************** 166 tests PASSED out of 181 tests run *************************************** List of 15 tests FAILED: * steady_state_operator/block.mod * deterministic_simulations/deterministic_model_purely_forward.mod * deterministic_simulations/deterministic_model_purely_backward.mod * block_bytecode/run_ls2003.m(1, 0, 1, 0) * block_bytecode/run_ls2003.m(1, 0, 2, 0) * block_bytecode/run_ls2003.m(1, 0, 3, 0) * block_bytecode/run_ls2003.m(1, 0, 4, 0) * block_bytecode/run_ls2003.m(1, 0, 6, 0) * block_bytecode/run_ls2003.m(1, 0, 7, 0) * block_bytecode/run_ls2003.m(1, 0, 8, 0) * block_bytecode/run_ls2003.m(1, 0, 1, 0) * block_bytecode/run_ls2003.m(1, 0, 2, 0) * block_bytecode/run_ls2003.m(1, 0, 3, 0) * block_bytecode/run_ls2003.m(1, 0, 4, 0) * block_bytecode/run_ls2003.m(1, 0, 6, 0) *************************************** *************************************** * DYNARE TEST RESULTS * * for make check-octave * *************************************** 179 tests PASSED out of 179 tests run *************************************** A full log can be found on karaba in '/var/tmp/dynare-master-check-Q9wlEjg7aU.log'.

1 0

Status of testsuite in 4.2 branch
by Sébastien Villemot 05 Jun '12

05 Jun '12

*************************************** * DYNARE TEST RESULTS * * for make check-matlab * *************************************** 150 tests PASSED out of 150 tests run *************************************** *************************************** * DYNARE TEST RESULTS * * for make check-octave * *************************************** 148 tests PASSED out of 148 tests run *************************************** A full log can be found on karaba in '/var/tmp/dynare-4.2-check-VwpN0YaN9j.log'.

1 0

Re: [DynareDev] Bug in dynare_estimation_init in 4.2.5
by Johannes Pfeifer 04 Jun '12

04 Jun '12

Actually, the correct solution is if options_.prefilter == 1 if options_.missing_data data=rawdata; bayestopt_.mean_varobs = zeros(n_varobs,1); for variable=1:n_varobs rdx = find(~isnan(rawdata(:,variable))); m = mean(rawdata(rdx,variable)); data(rdx,variable) = rawdata(rdx,variable)-m; bayestopt_.mean_varobs(variable) = m; end else bayestopt_.mean_varobs = mean(rawdata,1)'; data = rawdata-repmat(bayestopt_.mean_varobs',gend,1); end else data=rawdata; end % Transpose the dataset array. data = transpose(data); I pushed the fix to the 4.2 branch. Best, Johannes -------- Johannes Pfeifer Haußerstr. 29 72076 Tübingen Tel.: +49-(0)7071-6396184 Mobil: +49-(0)170-6936820 jpfeifer(a)gmx.de Von: Johannes Pfeifer [mailto:jpfeifer@gmx.de] Gesendet: Freitag, 11. Mai 2012 20:14 An: List for Dynare developers (dev(a)dynare.org) Betreff: Bug in dynare_estimation_init in 4.2.5 Dear all, dynare_estimation_init.m in 4.2.5 currently reads if options_.prefilter == 1 if options_.missing_data bayestopt_.mean_varobs = zeros(n_varobs,1); for variable=1:n_varobs rdx = find(~isnan(rawdata(:,variable))); m = mean(rawdata(rdx,variable)); rawdata(rdx,variable) = rawdata(rdx,variable)-m; bayestopt_.mean_varobs(variable) = m; end else bayestopt_.mean_varobs = mean(rawdata,1)'; rawdata = rawdata-repmat(bayestopt_.mean_varobs',gend,1); end end % Transpose the dataset array. data = transpose(rawdata); Hence, rawdata is overwritten with the demeaned data. This leads to wrong smoother plots. The corresponding part should be: if options_.prefilter == 1 if options_.missing_data data=rawdata; bayestopt_.mean_varobs = zeros(n_varobs,1); for variable=1:n_varobs rdx = find(~isnan(rawdata(:,variable))); m = mean(rawdata(rdx,variable)); data(rdx,variable) = rawdata(rdx,variable)-m; bayestopt_.mean_varobs(variable) = m; end else bayestopt_.mean_varobs = mean(rawdata,1)'; data = rawdata-repmat(bayestopt_.mean_varobs',gend,1); end end % Transpose the dataset array. data = transpose(data); I tried to push a fix for cherrypicking to 4.2 but I am not sure I succeeded. Best, Johannes -------- Johannes Pfeifer Haußerstr. 29 72076 Tübingen Tel.: +49-(0)7071-6396184 Mobil: +49-(0)170-6936820 jpfeifer(a)gmx.de

4 3