Commit Graph

260 Commits (a64ded92cdbb130f4d9f0b2760eedda397624128)

Author SHA1 Message Date
Stéphane Adjemian (Scylla) 788c528c84 Merge branch 'master' into use-dseries 2014-06-19 18:13:35 +02:00
Stéphane Adjemian (Charybdis) 4f02e58010 Added the possibility to pass a dseries object to the data command (the user can manipulate the data in the mod file, using dseries class methods, and use them for estimation without writing the data on disk). 2014-06-17 16:03:30 +02:00
Michel Juillard 499967f9a1 adding an option to extended path to control homotopic steps and
continue in case of failed case
2014-06-16 14:25:23 +02:00
Stéphane Adjemian (Charybdis) 06d1f66242 Fix initialization of the fields in options_.dataset + Cosmetic changes. 2014-05-21 16:47:58 +02:00
Stéphane Adjemian (Scylla) 0f62d74ee4 Fixed bug. Global options_.dataset.file must be initialized as an empty array. 2014-04-30 15:35:43 +02:00
Stéphane Adjemian (Scylla) 66d08ac3bf Merge branch 'master' into use-dynSeries
Conflicts:
	matlab/dynare_estimation_init.m
	matlab/global_initialization.m
	matlab/prior_posterior_statistics.m
	matlab/read_variables.m
	matlab/set_prior.m
	matlab/utilities/dataset/initialize_dataset.m
	preprocessor/ComputingTasks.cc
2014-04-30 10:10:30 +02:00
Sébastien Villemot 85f7af9133 Perfect foresight solver now uses a homotopy technique by default.
This commit introduces a "no_homotopy" option to restore the old behavior.

Ref #220
2014-04-10 16:39:06 +02:00
Sébastien Villemot bb1fd49629 Remove nonexistent global variable ex_det0_. 2014-04-08 17:19:55 +02:00
Sébastien Villemot 210d2f24e6 Trust-region solver is now the default solver. 2014-03-10 14:08:40 +01:00
Sébastien Villemot 5862099416 Merge pull request #607 from JohannesPfeifer/unique_varlist
Unique varlist and choosing endogenous variables for estimation
2014-02-04 05:14:05 -08:00
Sébastien Villemot 5308da2cad Upgrade the minimum requirement to MATLAB 7.5 (R2007b). 2014-02-03 15:52:54 +01:00
Johannes Pfeifer 85815ca651 Adds new option to select which variables to consider for estimation
First step for ticket #336
2014-02-03 13:10:31 +01:00
Johannes Pfeifer 15f0353d02 Make sure repeated runs of stoch_simul.m with loglinear option do not crash due to logged steady state 2014-01-29 19:52:20 +01:00
Stéphane Adjemian (Charybdis) 1ea7631930 Added new option for perfect foresight simulations (sim1 routine, available only with stack_solve_algo==0).
Try to reduce the size of the nonlinear system of equations by skipping the (last) periods for wich the residuals are
already (almost) zero. The number of periods is not constant during the Newton, the effective number of periods for
each iteration of the Newton is available in oo_.deterministic_simulation.vperiods.
2013-12-27 18:35:53 +01:00
Stéphane Adjemian (Scylla) 63986a0ebf Closes #567. 2013-12-18 16:44:31 +01:00
Stéphane Adjemian (Scylla) 4a4c06b781 Fixed bug (options_.subdraws does not exist). 2013-12-18 16:44:31 +01:00
Stéphane Adjemian (Penelope) 0c00151092 Merge branch 'master' into remove-dynDate-class
Conflicts:
	preprocessor/DynareBison.yy
2013-11-14 16:41:08 +01:00
Sébastien Villemot 80a2a6b712 Merge remote-tracking branch 'jpfeifer/irf_debug_feedback' 2013-11-13 14:26:58 +01:00
Houtan Bastani 0fdc18e7fb Merge branch 'ifc'
Conflicts:
	matlab/dynare_estimation_1.m
	matlab/global_initialization.m
2013-11-06 13:58:57 +01:00
Johannes Pfeifer b03697b342 Add possibility to initialize parameters from calibrated model 2013-11-06 13:50:46 +01:00
Stéphane Adjemian (Scylla) 8429321547 Merge branch 'master' into remove-dynDate-class 2013-11-06 12:43:06 +01:00
Johannes Pfeifer 0d669a73cb Add options for providing the variances, an identity matrix , and user specified matrices as proposal densities
Deals with #507 and #112
Includes a unit test
2013-11-04 19:09:24 +01:00
Stéphane Adjemian (Charybdis) ddd95361ba Cosmetic changes. Added isoctave function to replace exist('OCTAVE_VERSION'). 2013-11-04 10:54:45 +01:00
Stéphane Adjemian (Charybdis) f30b88f50c Changed default options_.initial_period (has to be a dates object). 2013-10-15 16:18:46 +02:00
Johannes Pfeifer 65a16fd293 Allow users to determine the threshold below which IRFs are suppressed.
- Prepares moving future IRF options to a substructure
- Adds new option for determining threshold
- Harmonizes threshold values across estimation and stoch_simul
- Fixes some header typos
2013-10-12 10:38:47 +02:00
Stéphane Adjemian (Charybdis) 28740370e6 Removed general maxit from options_ (maxit_). 2013-10-09 12:32:37 +02:00
Stéphane Adjemian (Charybdis) 8997ae8a70 Merge branch 'master' into maxit 2013-10-09 12:19:17 +02:00
Stéphane Adjemian (Charybdis) 8d8407f906 Changed default options for cmaes (reduced tolfun and tolx). 2013-10-08 15:56:14 +02:00
Stéphane Adjemian (Charybdis) 334d9976d6 Add interface to the main options of the simpsa optimization algorithm. 2013-10-08 15:18:14 +02:00
Stéphane Adjemian (Charybdis) 60e1d1b75e Changed the organization of the options for the dynare's implementation of the simplex optimization algorithm. 2013-10-08 12:55:11 +02:00
Stéphane Adjemian (Charybdis) f5c9621ca9 Changed the definition of the maximum number of function evaluations in dynare'es iplementation of simplex algorithm (mode_compute=8). 2013-10-08 11:11:35 +02:00
Stéphane Adjemian (Charybdis) 51be957fb6 Changed the organization of the options for gmhmaxlik (mode_compute=6) so that options can be set using the optim option of the estimation command. Added an option (targeted acceptance rate). 2013-10-04 16:12:14 +02:00
Houtan Bastani d369b8ad0e front end for maxit: ref #293, #262 2013-09-24 15:40:13 +02:00
Johannes Pfeifer 241fd07424 Add Geweke 1992 convergence diagnostics 2013-09-16 18:47:15 +02:00
Stéphane Adjemian (Charybdis) fd284003ce Merge branch 'master' into use-dynSeries
Conflicts:
	matlab/load_xls_file_data.m
2013-09-12 11:01:06 +02:00
Houtan Bastani de590fb2f7 bug fix: include nofunctions in global_initialization.m 2013-09-11 14:09:22 -04:00
Stéphane Adjemian (Charybdis) 8be8bf1b1b Recycle options_.dataset. If not empty (default) dataset field has to be a dynSeries object. 2013-09-07 16:05:01 +02:00
Stéphane Adjemian (Charybdis) 3dc372e5bc Added (command line) nointeractive option. 2013-07-10 12:02:12 +02:00
Johannes Pfeifer c4998f93d3 Transfer hardcoded osr options to options structure
Implements #423. To be done: add preprocessor options for tolf and maxit.
2013-06-24 22:53:28 +02:00
Stéphane Adjemian (Charybdis) 340bcc2739 Added an option for setting the number of points where the posterior kernel is evaluated when using mode_check. Reorganized the options_ global structure wrt mode_check. 2013-06-20 17:19:44 +02:00
Stéphane Adjemian (Charybdis) 39ef86f118 Partially reverted commit 06237375db. 2013-06-18 22:30:49 +02:00
Frédéric Karamé 06237375db Added the possibility to set the number of points in mode_check for computing the transversal cuts. 2013-06-18 16:16:56 +02:00
Stéphane Adjemian (Charybdis) cb2228acad Merge branch 'master' into experimental-mjdgges-threshold 2013-06-12 17:27:25 +02:00
Sébastien Villemot 61485ab809 Fix copyright notices 2013-06-12 17:04:46 +02:00
Stéphane Adjemian (Charybdis) a71b770fec Added default value for the threshold level of the 0/0 generalized eigenvalue test (1e-6). 2013-06-12 09:53:18 +02:00
Sébastien Villemot 9145d3691f Merge pull request #409 from rattoma/endo_prior_restrictions
New option to set prior (sign) restrictions irfs.
2013-05-31 01:33:32 -07:00
Marco Ratto 4923ba0952 Introduced new option that allows to set prior (sign) restrictions to irf's 2013-05-30 10:57:39 +02:00
Marco Ratto 7bef23f1b3 Allow asymmetric mode check plots, using the new option
mode_check_symmetric_plots (=1 at default, i.e. current behaviour)
2013-05-23 11:37:00 +02:00
Marco Ratto 09bc0a0aaa fixed bug with seeds in hybrid matlab-octave parallel clusters 2013-04-05 17:25:34 +02:00
Johannes Pfeifer 7518072e77 Fix several bugs related to estimated measurement errors
1. The first call to set_prior overwrote the first column of
estim_params_.var_endo storing the position of the variable with
measurement error in M_.endo_names with the position in
options_.var_obs. All subsequent calls to set_prior then lead to
crashes.
2. At the same time, for correlations of ME, the first column of
estim_params_.corrn still stored the position of the variable with
measurement error in M_.endo_names. But subsequent calls to it were done
as if it stored the position in options_.var_obs

I introduced two new variables in estim_params_ storing the respective
positions in var_obs so as to not necessitate changes in the
preprocessors.

3. For cases of calibrated measurement error correlations, the
covariance matrix was not updated.

4. Fixing a lot of smaller bugs related to measurement errors, including
some copy and paste errors
-
2013-03-21 20:51:12 +01:00