cd55ed749c
extended_path: fixing inititalization for PATH
...
(cherry picked from commit 7d29e917f77e7e20211e5be01544d86c64af8c65)
2016-05-24 18:08:33 +02:00
28c0c92ae8
fixing typos
...
(cherry picked from commit 86995a3bd478a3dc02919424aeb77e2a550a84c5)
2016-05-24 17:57:26 +02:00
3fa6a96bfb
Added homotopy.
...
Fixes the issue of paths containing spurious solutions for (stochastic)
perfect foresight models.
2016-05-24 17:28:24 +02:00
cfc6957625
Cosmetic changes.
2016-05-24 17:28:24 +02:00
8b5b7921f6
Improved solver for (S)EP.
...
Use previous solution as an initial condition for the perfect foresight problem.
2016-05-24 17:28:24 +02:00
80f1baad7e
Changed solver in simul_backward_nonlinear_model.
2016-05-24 17:28:24 +02:00
6c7f3f1932
Added input to pass sequence of shocks.
2016-05-24 17:28:24 +02:00
7d1d860a53
Fixed ep.init option.
...
Initialization of the perfect foresight solver (in extended path) with
the solution of the first order approximation of the model was broken.
If the value of options_.ep.init is "true"" (1) then the solution of the
first order approximation is used as an initial guess for the newton
lilke solver. If the value of options_.ep.init is "false" (0) the solver
is initialized with the steady state.
2016-05-24 17:28:24 +02:00
dabdda0506
Fixed wrong definition of a logical variable.
...
The second outputr returned by perfect_foresight_solver_core is the
max. abs. residual, not a dummy variable indicating success or failure
of the perfect foresight solver.
2016-05-24 17:28:24 +02:00
fbf2fae036
Changed option value for unscented integration nodes.
2016-05-24 17:28:24 +02:00
fdbd4fa7a7
Code factorization.
...
- Added routines for initializing and setting shocks in EP.
- Added a specialized routine for doing Monte Carlo around EP.
2016-05-24 17:28:24 +02:00
3bbac629ed
Cosmetic change.
...
Removed maximum_lead and maximum_lag in extended_path routines.
2016-05-24 17:28:24 +02:00
d74f315bfb
Fixed bug in (Stochastic) Extended Path algorithm.
...
Innovations were not correctly passed to the non linear solver. Closes #1128 .
2016-05-24 17:28:24 +02:00
4926b6c6ff
Added a routine the residuals of a model.
...
Takes a path for the endogenous variables and returns the residuals of
the dynamic equations. This routine is useful for solving the model with
the PEA approach.
2016-05-24 17:28:24 +02:00
ea1ebfa911
Added argument to simul_backward_nonlinear_model.
...
First input argument is a vector for the initial condition of the
endogenous variables. If empty, the steady state of the model is used.
2016-05-24 17:28:24 +02:00
e507a6d0a9
Fixed copyright header.
2016-05-24 17:28:24 +02:00
8958b7ef98
Cosmetic changes.
2016-05-24 17:28:24 +02:00
3a1f74d7a7
Fixed typo.
2016-05-24 17:28:24 +02:00
13ca15a278
Allow (S)EP with arbitrary sequence of innovations.
...
The third input argument of extended_path Matlab/Octave's routine is the
sequence of shocks (T*n array, where n is the number of exogenous
variables and T is the size of the sample). If the third argument is
empty, the (stochastic) extended path is run with gaussian
innovations (this corresponds to the previous behaviour).
TODO:
- Fix the compatibility with ep.replic_nbr
- Check the 'calibrated' mode.
2016-05-24 17:28:24 +02:00
b60bd7b36b
Removed globals from extended_path routine.
2016-05-24 17:28:24 +02:00
ee78ad2049
Improved execution speed.
...
Removed some calls to bsxfun which is not optimal on sparse matrices. I
only removed the calls where I identified bottlenecks (with a Smets and
Wouters model), more tests are needed to decide if we have to remove other
occurences of bsxfun on sparse matrices.
2016-05-24 17:26:06 +02:00
be0f6230ad
Cosmetic changes.
...
- Use a switch-case block.
- Added a warning when the user tries to solve a linear(ized) model
with solve_algo different from 0 (for a linear model).
- Added an error message if the user try to solve a linearized model
with stack_solve_algo=6 (not implemented).
2016-05-24 17:26:06 +02:00
1815eb8e56
Code factorization.
2016-05-24 17:26:06 +02:00
8a163842d0
Removed oo_ from sim1_linear routine.
2016-05-24 17:26:06 +02:00
53747cb082
Fixed lmmcp option.
...
This option may be used in extended_path and perfect_foresight_solver commands.
2016-05-24 17:26:06 +02:00
e0be60710c
Removed oo_ from sim1_purely_{backward,forward} routines.
2016-05-24 17:26:06 +02:00
290ce5db68
Removed oo_ from sim1_lbj routine.
2016-05-24 17:26:06 +02:00
674c9ab286
Removed oo_ from sim1 routine.
2016-05-24 17:26:06 +02:00
3e8dbcfc7e
Set mode_files in such a way that it can be handled with key-value pair.
...
We need a single mode file that contains variable xparams = [x1 x2 x3] all multiple modes, one per column.
Fixes #1199
2016-05-22 23:15:18 +02:00
d8fea3ff13
Correlations and measurement errors in identification:
...
1) Filter out measurement errors with error message that suggests to explicitly write measurement errors in model definition
2) allow identification checks with correlations, by switching to numerical derivatives
2016-05-22 23:10:01 +02:00
389f43019d
Put fields of OSR in M_ into workspace to restore compatibility with 4.4.3
2016-05-22 11:41:54 +02:00
d10f8b42d7
Fix bug in convert_dyn_45_to_44.m if bayestopt_ is empty
2016-05-22 11:41:54 +02:00
03563e012b
Allow for pass OSR parameter bounds to optimizer
2016-05-22 11:41:54 +02:00
9774d0544d
Initialize fields of M_.osr to empty in global_initialization.m
2016-05-22 11:41:54 +02:00
676182f550
Cosmetic fix to dynare_minimize_objective.m
2016-05-22 11:41:54 +02:00
3df1a1275f
Merge pull request #1185 from JohannesPfeifer/bytecode_fixes
...
Bytecode fixes
2016-05-22 10:32:56 +02:00
13d42e05a5
Add missing else-clause in simulated_moment_uncertainty.m
...
Fixes crash in unit tests
2016-05-22 10:03:56 +02:00
0521aa4e09
Merge pull request #1188 from JohannesPfeifer/slice_marco
...
Add slice and factorization of posterior samplers
2016-05-22 01:45:14 +02:00
161f674dd9
Fix two TeX loaders where apostrophe was missing
2016-05-20 12:43:52 +02:00
7c97d7c662
Allow displaying 0 rows in disp_dr.m
2016-05-20 12:42:43 +02:00
2baf88da47
Remove adaptive_metropolis_hastings
2016-05-19 23:16:29 +02:00
89fd14f026
Filter out unit root cases that lead to crashes
2016-05-19 18:57:47 +02:00
1f71331e58
Fix dynareParallelGetFiles.m call to random_walk_metropolis_hastings
2016-05-19 17:43:48 +02:00
12ee5b7276
Fix copyrights and references to random_walk_metropolis_hastings headers
2016-05-19 17:15:31 +02:00
781ea45777
Remove old independent_metropolis_hastings routines
2016-05-19 14:37:05 +02:00
3073988ac1
Fix vector dimension for independent_metropolis_hastings
2016-05-19 14:37:05 +02:00
86fcde0879
Cosmetic changes to dynare_estimation_1.m and store_smoother_results.m
2016-05-19 14:37:05 +02:00
4898a66d2a
Allow passing of optim option for TaRB
2016-05-19 14:37:05 +02:00
90ab263587
Fix location of TaRB options
2016-05-19 14:37:05 +02:00
413a264b21
Make read_key_value_string.m compatible with sublists
2016-05-19 14:37:05 +02:00
091f94221f
Delete unused TaRB_metropolis_hastings_core.m
2016-05-19 14:37:05 +02:00
c7e8489481
Rename autocorr into dyn_autocorr.m as it does not mirror the behavior of the econometric toolbox function
2016-05-19 14:37:05 +02:00
1d6961cc4c
initialize mode field in slice sampler options
2016-05-19 14:37:05 +02:00
e5ab7ed992
fixed unknown options warning messages
2016-05-19 14:37:05 +02:00
088db78118
Document computation of Inefficiency factors
2016-05-19 14:37:05 +02:00
ebe34bc40f
Make display of inefficiency factors use existing table util [thanks to Johannes]
2016-05-19 14:37:05 +02:00
7b3c42c6e1
provisions for reworked posterior sampling options:
...
- handle sub lists of individual samplers
- split checks in dynare_estimation_init.m and before running posterior_sampler.m [invhess checks]
- posterior sampler options checks moved from initial_estimation_checks.m to check_posterior_sampler_options.m
- added use_mh_covariance_matrix to imh and rwmh
- slice re-sets mode_compute=0 cova_compute=0
- updated test function
2016-05-19 14:37:05 +02:00
cf6e3cb14c
preprocessor: rework posterior sampler options, #1177
2016-05-19 14:37:05 +02:00
35a1c7ac17
Commented options for slice sampler, including default values and associated restrictions/default for main options_ fields
2016-05-19 14:34:09 +02:00
9c62021d3c
Move TaRB to posterior_sampler_iteration.m [PATCH from Johannes: thanks a lot]
2016-05-19 14:34:09 +02:00
0c01565298
Allow sampler specific options via optim;
...
bug fixes on options logic
2016-05-19 14:34:09 +02:00
22f51d1e75
moved autocorr to missing matlab econometrics toolbox [it is not in stats toolbox]
2016-05-19 14:34:09 +02:00
4445f17efa
Manual merge with commit history of metropolis_hastings_initialization.m and random_walk_metropolis_hastings_core.m
2016-05-19 14:34:09 +02:00
357e3c2ac7
Make posterior_sampler_initialization.m compatible with new form of prior_draw.m
2016-05-19 14:34:09 +02:00
8e751be5ee
bug fix for non integer Nc
2016-05-19 14:34:09 +02:00
e69c5f6864
Bug fix for odd Nc
2016-05-19 14:34:09 +02:00
8bd963de64
Fill in posterior_mode with info from posterior samples.
2016-05-19 14:34:09 +02:00
b830805cb6
Trap empty d [e.g. from slice sampler]
2016-05-19 14:34:09 +02:00
a96dd5b964
for slice, always initialize empty invhess unless a new chain is initialized from a mode file
2016-05-19 14:34:09 +02:00
9089fc340c
Initialize posterior_sampler_options.
2016-05-19 14:34:09 +02:00
46908d20c6
Provisions for new posterior sampler routines that factorize the individual iteration of individual samplers.
...
I contains a quick fix to adaptive_posterior_sampler.m, which cannot be embedded in the new structure.
2016-05-19 14:34:09 +02:00
c30b6f20a6
Added routines that factor out posterior samplers into the iteration routine posterior_sampler_iteration.m.
...
It generalizes the random_walk_metropolis_hastings.m structure but adds two new items:
- check_posterior_sampler_options.m which is a wrapper for method specific options (stored in options_.posterior_options)
- posterior_sampler_iteration.m which is a wrapper of the individual iteration of any posterior sampler.
It already embeds, with parallelization implementation:
- random_walk metropolis hastings
- independent metropolis hastings
- slice sampler
It also contains a quick fix for TARB, although the latter should be embedded in posterior_sampler_iteration.m as well.
Any new posterior sampler can be simply added to posterior_sampler_iteration.m, with wrapper to specific iterations in check_posterior_sampler_options.m
2016-05-19 14:34:09 +02:00
b1b901fc61
Added SLICE sampler core routines
2016-05-19 14:34:09 +02:00
951dfe8ff4
When mh_posterior_mode_estimation, trap cases where the prior mode is at the boundary.
2016-05-19 14:34:09 +02:00
a3ab6de6c8
Added function to compute of inefficiency factors, used in McMCDiagnostics.m
...
Requires missing autocorr (available in some MATLAB toolboxes).
Requires factor out CutSample in dynare_estimation_1.m
2016-05-19 14:34:09 +02:00
0e2e1376c9
Fix bug in simulated moments
...
Closes #1105
2016-05-18 22:51:20 +02:00
58eb60c95d
fix copyright dates, headers
2016-05-18 15:06:49 +02:00
6a0de7a724
Merge pull request #1189 from rattoma/gsa
...
gsa and identification fixes
2016-05-18 15:01:19 +02:00
c05c66cbaa
Filter out error code 6 in dsge_var_likelihood.m
...
Crashes otherwise
2016-05-17 20:56:25 +02:00
42170c6c13
Fixes around models with unit roots.
2016-05-17 11:47:07 +02:00
c9bc685049
Fix determination of full rank subspace of simulated moment uncertainty
2016-05-17 09:38:06 +02:00
f0b346b397
added waitbar, to monitor computations [especially useful for large models]
2016-05-17 08:41:55 +02:00
7c8878c071
Allow neighborhood_width sampling in Morris + bug fix.
2016-05-17 08:41:16 +02:00
28aeb9f308
bug fix
2016-05-17 08:40:32 +02:00
5723e7ea58
build system: remove support for 32-bit Matlab on OS X
2016-05-13 10:53:55 +02:00
89667ea8da
remove unused file. closes #1172
2016-05-11 15:12:27 +02:00
31f8d61586
make estimation honor steady state nocheck option
2016-05-10 15:54:11 +02:00
ccb197e74f
fix copyright dates
2016-05-09 12:42:58 +02:00
5e5157e375
loglinear: bug correction
2016-05-06 10:12:12 +02:00
67ea280773
adding missing semi-colon
2016-05-06 10:11:53 +02:00
ef232ac436
fixed log_variable function
2016-05-05 20:53:22 +02:00
3c7c2f46a4
more fixes for loglinear with lead/lagged exogenous variables
2016-05-05 20:41:02 +02:00
7e13fe5ef7
fix loglinear option with leaded or lagged exogenous variables
2016-05-05 20:41:02 +02:00
e07d97a16e
Merge pull request #1186 from rattoma/gsa
...
gsa and identification fixes
2016-05-05 19:19:10 +02:00
1b769d1d5f
1) fixed bug with initialization of infox
...
2) distinguish between no solution (iwrong index) and violation of prior restrictions (inorestriction)
3) smirnov tests for indeterminacy and explosive roots should be done EXCLUDING no solution cases
2016-05-05 16:53:18 +02:00
8e1d225832
Allow to perform neighborhood_width sampling around calibrated values;
2016-05-05 16:18:17 +02:00
0e402fa7e9
Filter out cases where too few samples are available for ANOVA estimation
2016-05-05 16:11:53 +02:00
8b54354a27
Make identification compliant with calibration parameter set [bug fix]
2016-05-05 16:08:14 +02:00
5f32b80a27
Fix error codes for bytecode in perfect_foresight_solver_core.m
...
If it fails, 1 must indicate error, not 0
2016-05-05 10:52:17 +02:00
465f55bb0e
Correct evaluation of residuals in dynare_solve.m when exitflag does not clearly indicate solution
...
Otherwise, it crashes with bytecode
2016-05-05 10:46:39 +02:00
c6f705a8b9
Correct setting of info in dr_block.m if eigenvalue is close to 0/0
...
Must be the same as in dyn_first_order_solver.m
2016-05-05 10:08:52 +02:00
bebcfffe04
fix license, file copyright errors
2016-05-04 16:30:16 +02:00
25121bca4f
fix copyright dates
2016-05-04 16:05:31 +02:00
b364dd1d4c
Account for Matlab 2016a in installer and mex-folder
...
Note that 32bit is not supported anymore
(cherry picked from commit e37b32b01534ffe9a5a5ec3f00f745720b75a83f)
2016-05-04 11:12:35 +02:00
6593c433f3
Revert "Account for Matlab 2016a in installer and mex-folder"
...
This reverts commit 6072aa0b46
2016-05-03 22:20:10 +02:00
6072aa0b46
Account for Matlab 2016a in installer and mex-folder
...
Note that 32bit is not supported anymore
(cherry picked from commit e37b32b01534ffe9a5a5ec3f00f745720b75a83f)
2016-05-03 15:24:23 +02:00
c48a2659e5
Fix warning message that confused structural shocks with measurement errors
2016-05-01 17:52:57 +02:00
6eb2e43432
Merge pull request #1171 from JohannesPfeifer/discretionary_policy
...
discretionary_policy_1.m: keep state space fixed even if state variab…
2016-04-18 22:17:42 +02:00
d1735e1d9e
discretionary_policy_1.m: keep state space fixed even if state variable gets coefficient of 0 in solution by including appropriate 0 column. (Thanks to Junior Maih)
...
Reverts 3b64c37cb3
2016-04-18 21:48:28 +02:00
e8c430a923
replaced transtion_matrix.m by kalman_transition_matrix.m
2016-04-16 17:21:42 +02:00
3d6c184566
Merge pull request #1168 from JohannesPfeifer/filter_tests
...
Improve speed of filtering unit tests and clean up setting of options
2016-04-15 09:50:49 +02:00
a047b42dd3
Merge pull request #1167 from JohannesPfeifer/shock_decomp_fix
...
Add missing deblank to fieldname setting in shock_decomposition.m
2016-04-15 09:50:39 +02:00
a21aa064c9
Merge pull request #1166 from JohannesPfeifer/kalman_fixes
...
Kalman fixes
2016-04-15 09:50:25 +02:00
c509f6d463
Add missing deblank to fieldname setting in shock_decomposition.m
2016-04-15 09:41:38 +02:00
3542d086ae
Transform hard-coded bandpass filter order into option
2016-04-15 09:23:35 +02:00
800d79d6e5
add option colormap for shocks_decomposition
2016-04-15 09:02:53 +02:00
de567377c3
adding groups of shocks for shock_decomposition
...
consistency checks, documentation and test case
are still missing
2016-04-15 09:02:53 +02:00
8908d46567
Initialize s to make sure univariate_kalman_filter_d.m does not crash if newRank is 0 initially
2016-04-14 20:11:49 +02:00
9a9b8f2a70
Account for smoother setting parameter count fields in dynare_estimation_init.m
...
Otherwise, subsequent calls to the smoother will result in crashes
2016-04-14 20:11:22 +02:00
7c53ea1e96
Fixed unit tests.
...
(cherry picked from commit 2cdfc0518350e4f26dd406b1730f2cf20ce29e07)
2016-04-14 17:21:37 +02:00
a8cc21eb97
Merge pull request #1163 from JohannesPfeifer/Smoother_fixes
...
Various fixes and documentation improvements related to smoother, trends and selected_variables_only option
2016-04-12 14:22:19 +02:00
62efd9930e
Merge pull request #1148 from JohannesPfeifer/foresight_imaginary
...
Add check whether real part of complex solution solves the model
2016-04-12 13:06:26 +02:00
8f1eb47a5e
Merge pull request #1104 from JohannesPfeifer/solve_algo_0
...
Only accept steady state when fsolve retuns with normal return code 1
2016-04-12 13:05:28 +02:00
aa1a0b5e25
Merge pull request #1052 from JohannesPfeifer/lin_solve_robust
...
Integrate robust linear solver for stack_solve_algo=0
2016-04-12 12:06:22 +02:00
d7e4469a28
Merge pull request #1153 from JohannesPfeifer/steady_check_flag
...
Make evaluate_steady_state.m honor nocheck flag
2016-04-12 12:04:57 +02:00
6ad876cc18
Rename write_smoother_results to store_smoother_results.m to avoid confusion about its purpose
2016-04-12 11:37:12 +02:00
f5bd4c6b3a
Fix bug where smoother selected wrong observables with selected_variables_only option
...
Closes #1161
2016-04-12 11:36:43 +02:00
df20a394fc
Fix variable sorting in with ML without selected_variables_only, which was erroneously in decision rule order
...
Also fixes wrong output when selected_variables_only was used
2016-04-12 11:30:14 +02:00
be2221286c
Add note on setting of bayestopt_.mf to DsgeSmoother.m
2016-04-12 10:52:40 +02:00
98384eb6f2
Document variable ordering in various headers
2016-04-12 10:52:37 +02:00
00bfa2a0a9
Fix header of dynare_resolve.m
2016-04-12 10:52:36 +02:00
b749a3ce75
Improve header and variable naming in write_smoother_results.m
2016-04-12 10:52:07 +02:00
a78ebbce72
Document setting of element of restricted state space
2016-04-12 10:51:33 +02:00
6d35dad894
Remove duplicate setting of bayestopt_.mf* in dynare_estimation_init Closes #820
2016-04-12 10:46:44 +02:00
1def8a409b
Merge pull request #1158 from JohannesPfeifer/higher_moments
...
Save skewness and kurtosis when simulated moments are requested
2016-04-12 10:46:40 +02:00
efee7b1a47
Remove duplication of restrict_var_list in bayestopt_
2016-04-12 10:43:28 +02:00
80086ff4ab
Clarify naming of var_obs_index to indicate it refers to decision rule order
2016-04-12 10:42:44 +02:00
6dddd7a8d4
Add corr.m to missing/stats
2016-04-09 15:22:40 +02:00
f85d2ef970
Make shock_decomposition.m rely on smoothed deviations from mean
...
Necessary after adding trend and mean to smoothed variables
2016-04-09 09:45:21 +02:00
d737c7d1d8
Allow corner solution as starting point for MCMC
...
Bound is treated as admissible solution in previous steps like mode-finding, so it should be here, too
2016-04-09 09:45:21 +02:00
7e56302a04
Assure that log-file is closed when aborting metropolis_hastings_initialization.m
2016-04-09 09:45:21 +02:00
352a4fd3ae
Port bugfix b8c6c87908 to area graphs of conditional_forecast
2016-04-09 09:45:21 +02:00
1d13a5dd02
Make imcforecast.m account for presence of trends
2016-04-09 09:45:21 +02:00
056548ba76
Merge pull request #1152 from JohannesPfeifer/headers
...
Cosmetic changes to various function headers
2016-04-08 23:29:16 +02:00
358ba0181c
Save skewness and kurtosis when simulated moments are requested
...
Closes #1157
2016-04-06 09:23:54 +02:00
1628f01fdb
fixing problems with Ramsey policy and auxiliary variables
2016-04-04 17:11:03 +02:00
70bcef4933
analytic derivation: cleaning up
2016-04-01 18:45:19 +02:00
e446aaddb1
analytic derivation: use <fname>_static_params_deriv where needed
2016-04-01 18:45:19 +02:00
2313f20a35
completing replacement of auxiliary variables in static model
2016-04-01 18:45:19 +02:00
bf5a3ab6da
Add headers to identification routines
2016-03-31 11:20:01 +02:00
Michel Juillard
Stéphane Adjemian (Charybdis)
Marco Ratto
Johannes Pfeifer
Houtan Bastani