qz_criterium = 1+1e-6
- stoch_simul
- osr
- check
- dynare_estimation_1 with lik_init =2 or 3
qz_criterium = 1+1e-6 for dynare_estimation_1 with lik_init = 1
This correct a bug in estimation and computation of the posterior distribution of moments of endogenous variables when the priors permit roots too close to 1.
(--with-openmp) is not passed by an environment variable anymore. The function set_dynare_threads changes the default value of the
number of threads (default is 1) in the options_.threads structure. Changed calls to sparse_hessian_times_B_kronecker_C and
A_times_B_kronecker_C dlls accordingly.
1) safe management of remote folder;
2) shh scp (and windows equivalent) commands are concentrated in the master;
3) management of remote crashes;
4) begin building option to interrupt remote processes;
5) better parallel waitbar: pops up only at STARTUP (can be minimized subsequently); adaptive dimension;
(2) Speed improvement in second order simulations (replaced call to matlab's kron function by call to
A_times_B_kronecker_C).
(3) Removed useless globals.
(4) Cosmetic changes and corrections on headers.
* give the possibility of calibrating measurement errors in the "shocks" blocks (only for observed endogenous variables)
* M_.H is now initialized in the preprocessor
* only one "varobs" statement is now accepted in a MOD file
- reverting part of last change to handling of Qi and Ri in ComputingTasks.cc: r is the number of lags present in the restrictions
- fixing handling of Dirichlet option in mhm_input.dat. This fixes the strange Signal messages when running C executables.
- fix path in test_upper_cholesky.mod
by numgrad routines to compute the gradient. The default value (defined in global_initialization.m) for this parameter is 1e-6. The
value of epsilon is stored in options_.gradient_epsilon.
git-svn-id: https://www.dynare.org/svn/dynare/trunk@3335 ac1d8469-bf42-47a9-8791-bf33cf982152
* removed "options_.simul", and instead test if "options_.periods" is non-zero
* test for the incompatibility of options "periods" and "hp_filter" in "stoch_simul.m", instead of in the preprocessor
Reference manual:
* removed "simul" options, updated "periods"
* updated "order" option (for 3rd order)
* added "k_order_solver" option
* give some hints for installing a compiler for users of MATLAB for Windows
git-svn-id: https://www.dynare.org/svn/dynare/trunk@3188 ac1d8469-bf42-47a9-8791-bf33cf982152
(the terminal condition is y_{T} = y^{\star}), other possible values
are 1 (terminal condition is y_{T+1}=y_{T}) and 2 (terminal
condition is y_{T+1}=TransitionMatrix*y_{T}, where TransitionMatrix
is given by the first order approximation of the reduced form model).
* Added mode options_.terminal_condition=2 in perfect_foresight_simulation.m.
git-svn-id: https://www.dynare.org/svn/dynare/trunk@3176 ac1d8469-bf42-47a9-8791-bf33cf982152
* added interface in the MOD file, with a new option "aim_solver" to stoch_simul and estimation
* documented the option in the reference manual
git-svn-id: https://www.dynare.org/svn/dynare/trunk@3059 ac1d8469-bf42-47a9-8791-bf33cf982152
- corrects some mod files.
- In steady command, get check argument from bytecode dll
git-svn-id: https://www.dynare.org/svn/dynare/trunk@3051 ac1d8469-bf42-47a9-8791-bf33cf982152
* Added solve_algo=5 for steady
* Remove obsolete method option of simul
* Added various checks to avoid unimplemented combinations of bytecode/block/solve_algo/stack_solve_algo
git-svn-id: https://www.dynare.org/svn/dynare/trunk@2882 ac1d8469-bf42-47a9-8791-bf33cf982152
- the options "sparse_dll" and "sparse" are no more available. They are replaced by combinations of block (for block decomposition) and bytecode (for model stored in a binary file)
- markowitz is now an option of simul and steady commands
git-svn-id: https://www.dynare.org/svn/dynare/trunk@2873 ac1d8469-bf42-47a9-8791-bf33cf982152
- mfs: new option for 'steady' and 'model' commands. Determines the equation belonging to the set of feedback variables.
mfs = 0 => all variables are considered as feedback variables (default value)
mfs = 1 => using only naturally normalized equation as potential recursive equations (all variables assigned to unnormalized equations are considered as feedback variable)
mfs = 2 => adding to the set of potential recursive equation with mfs = 1 the linear equation in endogenous variable normalized (all variables assigned to nonlinear unnormalized equations are considered as feedback variable)
mfs = 3 => adding to the set of potential recursive equation with mfs = 2 the non linear equation in endogenous variable normalized
- correction of few buggs in simulate.dll
- block_mfs_dll: new option for 'steady' command. Use simulate.dll to solve the steady state model (speedup the computation of the steady-state and the homotopy)
git-svn-id: https://www.dynare.org/svn/dynare/trunk@2866 ac1d8469-bf42-47a9-8791-bf33cf982152
+ Added a new option for likinit=2 used to define the numbers on the
initial diagonal Pstar matrix.
git-svn-id: https://www.dynare.org/svn/dynare/trunk@2828 ac1d8469-bf42-47a9-8791-bf33cf982152
- oo_.mean, oo_.var, oo_.gamma_y contains all selected variables
- moments of non-stationary variables are set to NaN
options_.Schur_vec_tolerance lowered to 10^-11
git-svn-id: https://www.dynare.org/svn/dynare/trunk@2810 ac1d8469-bf42-47a9-8791-bf33cf982152
decomposition (more tests are needed).
The results are saved in oo_.PosteriorTheoreticalMoments.dsge.ConditionalVarianceDecomposition.
Contrary to the asymptotic variance decomposition, we do not report
contribution shares but contribution levels of each structural shock.
LIMITATIONS:
* Won't work in a model with measurement errors.
* Won't work in a model with correlated shocks.
* The routines do not compute the covariance decompositions.
git-svn-id: https://www.dynare.org/svn/dynare/trunk@2719 ac1d8469-bf42-47a9-8791-bf33cf982152
+ Added new file for prior sampling (prior_sample.m).
+ Undo previous change on prior_draw.m (transposition of pdraw).
+ Bug correction in prior_draw.m.
+ Added field in options_: the default number of mc simulations in the
prior distribution.
git-svn-id: https://www.dynare.org/svn/dynare/trunk@2431 ac1d8469-bf42-47a9-8791-bf33cf982152
+ Fixed a bug introduced in the previous commit.
+ Added a threshold parameter for the complex blocks in the upper
triangular matrix T in lyapunov_symm.m (new field in options_)
+ Cosmetic changes.
git-svn-id: https://www.dynare.org/svn/dynare/trunk@2414 ac1d8469-bf42-47a9-8791-bf33cf982152
* Added a new tolerance parameter specific to the iteration on the riccati equation.
* Added a kalman filter routine allowing for missing observations.
* I do not distinguish anymore models with and without measurement errors (the same m file is used for both models to evaluate the likelihood). For a model without measurement errors H hat to be set to 0 scalar.
git-svn-id: https://www.dynare.org/svn/dynare/dynare_v4@2148 ac1d8469-bf42-47a9-8791-bf33cf982152
+ Correction of a bug related to ferhat's recent commits (options_.model_mode has to be declared somewhere).
git-svn-id: https://www.dynare.org/svn/dynare/dynare_v4@2013 ac1d8469-bf42-47a9-8791-bf33cf982152
for start, options_.useAIM = 0 is set by default in global_initialization.m so that system uses mjdgges by default.
If AIM is to be used, options_.useAIM = 1 needs to be set either in the model <>.mod file, before invoking, estimate and/or stoch_simul, or by issuing appropriate command for estimate and/or stoch_simul.
GP July '08
git-svn-id: https://www.dynare.org/svn/dynare/dynare_v4@1966 ac1d8469-bf42-47a9-8791-bf33cf982152
* Added function numgrad3.m. This new function uses a three point formula to compute the gradient. By default Dynare uses the two point formula. By setting options_.gradient_method=3 Dynare switches to the three point formula. Note that an input argument has been added to csminwel.
* Added automatic detection of needed constant in dsge-var model (may be problematic is some cases)
git-svn-id: https://www.dynare.org/svn/dynare/dynare_v4@1935 ac1d8469-bf42-47a9-8791-bf33cf982152