Michel Juillard
9fa92b0d02
fixing error message
2014-11-14 07:15:24 +01:00
Stéphane Adjemian (Telemachus)
a8e7c30e6a
Added @dseries/exist method.
2014-11-13 16:53:06 +01:00
Johannes Pfeifer
cc96d46911
Transfer hard-coded verbosity of simplex algorithm into an option
2014-11-10 19:54:44 +01:00
Johannes Pfeifer
7c59edead2
Make simplex_optimization_routine.m usable outside of estimation
...
Removes hard-coded parameter names extracted from bayestopt_ by handing them over explicitly
2014-11-10 19:53:55 +01:00
Johannes Pfeifer
c3467ddca2
Simplex: return only scalar best value instead of full vector
2014-11-10 19:41:50 +01:00
Stéphane Adjemian (Sedna)
bbf6ea50b0
Added workaround for bug in some Matlab versions (wrong type).
2014-11-10 11:21:05 +01:00
Stéphane Adjemian (Telemachus)
0691b08303
Adapated internals routine (name of dynTest routine has changed).
2014-11-09 22:20:43 +01:00
Stéphane Adjemian (Telemachus)
6557849b30
Updated m-unit-tests module.
2014-11-09 22:20:18 +01:00
Stéphane Adjemian (Telemachus)
a12e9d684a
Force type consistency when comparing actual results and expected
...
results in unit tests (use logical type).
2014-11-09 22:17:46 +01:00
Stéphane Adjemian (Telemachus)
8fedac4d5e
Replaced calls to dyn_assert by calls to dassert.
...
This routine is used to compare objects i -n unit tests.
2014-11-08 09:28:53 +01:00
Stéphane Adjemian (Telemachus)
479189ef47
Updated path in dynare_config.
...
For m-unit-tests module.
2014-11-07 22:41:25 +01:00
Stéphane Adjemian (Telemachus)
f2aabb1f0d
Added m-unit-tests as a submodule.
2014-11-07 22:40:31 +01:00
Stéphane Adjemian
1c62420909
Removed matlab/utilities/tests subfolder.
2014-11-07 22:31:23 +01:00
Houtan Bastani
e6789a3707
Merge pull request #761 from JohannesPfeifer/message_test_calibration
...
Clarify message in test_for_deep_parameters_calibration.m
2014-11-07 17:27:15 +01:00
Houtan Bastani
1f25e7d479
Merge pull request #757 from JohannesPfeifer/fix_display
...
Add missing run index to looped variable in resol.m
2014-11-07 17:25:50 +01:00
Houtan Bastani
a1a0cc098b
skipline: simplify code
2014-11-07 16:44:05 +01:00
Houtan Bastani
f98a41007e
skipline: fix function header
2014-11-07 16:44:05 +01:00
Houtan Bastani
ae52f7615c
bug fix: skipline
2014-11-07 16:44:05 +01:00
Stéphane Adjemian
6edef09aba
Added fake input argument in @dates/isequal.
2014-11-07 16:12:47 +01:00
Stéphane Adjemian
d77dec9726
Added optional tolerance parameter in @dseries/isequal method.
2014-11-06 15:43:23 +01:00
Houtan Bastani
884cbc3fbe
dseries: bug fix: add delimiter for importdata for .csv files
2014-11-06 14:46:27 +01:00
Houtan Bastani
3f4f348a0a
dseries: variable in error messages isn't set
2014-11-06 14:34:05 +01:00
Houtan Bastani
9a966151fa
fix typo
2014-11-06 13:48:53 +01:00
Johannes Pfeifer
2a67e2a306
Take care of imaginary numbers in perfect foresight simulations
...
Finishing with imaginary parts now does not count as a solution and triggers a new homotopy step.
2014-11-06 09:08:50 +01:00
Johannes Pfeifer
cb5d3df6a0
Computation of the loss function in the presence of unit root variables was incorrect
...
Some elements were simply left out. This commit now mimics the computations as in th_autocovariances.m and makes sure the loss function coincides with the one that is obtained by reading out the covariance from oo_.var
2014-11-03 18:05:15 +01:00
Johannes Pfeifer
669016167e
Fix bug in osr where moments were not based on optimal parameter draw
...
M_.params is global and was set by csminwel1 to the last value tested; this does not necessarily coincide with the optimal parameter vector, which may have occurred earlier. This commit explicitly sets the optimal parameter vector.
2014-11-03 18:01:04 +01:00
Johannes Pfeifer
7b1663281b
Transform objective function in osr to full matrix
...
If the objective function only has one element, the scalar product of a sparse matrix and a full matrix is sparse (in contrast to two or more elements). This crashes the osr code subsequently.
2014-11-03 15:29:21 +01:00
Johannes Pfeifer
6bc9b88401
Add reordering of second order derivatives to stochastic_solvers.m
...
It was erroneously completely moved to dyn_second_order_solver.m in the 4.3 branch when cleaning up dr1.m. Without this reordering, decision rules for exogenous deterministic variables at second order are wrong
2014-11-02 19:34:55 +01:00
MichelJuillard
283912be53
Merge pull request #770 from JohannesPfeifer/Ramsey_aux_vars
...
Ramsey aux vars
2014-11-02 15:16:44 +01:00
Johannes Pfeifer
ecbe428bd7
Fix computation of objective function in OSR if covariances are specified
...
Due to the preprocessor adding entries for all variable combination into i_var, variables contained in covariances obtained a wrong weighting. By only selecting the unique entries, this cannot happen anymore. Moreover, the computation intensity of the objective does not increase quadratically in the objective anymore.
2014-11-02 12:49:11 +01:00
Michel Juillard
491301c67b
th_autocovariances.m creates Gamma_y{nar+2} (variance decomposition)
...
even if there is a single shock. In that case variance decomposition
is one. It is better if Gamma_y has always the expected
size. disp_th_moments.m only displays variance decomposition if there
is more than one shock.
2014-11-02 11:17:27 +01:00
Michel Juillard
fbbe98815b
fixing bug introduced in commit 6eb3a3d
when displaying theoretical
...
moments for a model with a single exogenous variable
2014-11-01 09:15:48 +01:00
Johannes Pfeifer
c2da796153
Fix distinction between initial values provided to dyn_ramsey_static.m and stale unchanged initial values in oo_.steady_state
...
In case of no steady state file, they are identical, but with a steady state file, they are not. Moreover, this fixes a problem with the dimension of the input to the steady state file. ys was not initialized and had wrong dimensions
Also adds comments to file.
2014-10-30 13:31:57 +01:00
Johannes Pfeifer
3a9c273535
Allow for check of Hessian at order>2 in model_diagnostics.m
2014-10-29 19:37:03 +01:00
Johannes Pfeifer
c1999443ce
Condition singularity warning on unit root check
...
When singularity is detected, try to compute eigenvalues to see if unit root is present and issue warning according to this check
2014-10-29 19:33:33 +01:00
Johannes Pfeifer
a159442935
Fix message in dynare_estimation_init.m
...
If some parameters are NaN after computing the steady state, the message erroneously said that parameters had been changed. In a check for equality, NaN is not equal to NaN. Thus, NaNs are now taken care of separately.
2014-10-29 09:02:29 +01:00
Stéphane Adjemian (Charybdis)
9300a061aa
Fixed bug (appearing only with Matlab and legacy data interface) if the m data file is in the current directory.
...
If the m data file is in the current directory, the first output of
fileparts(options_.datafile) is an empty string. In Matlab the command
cd('') fails, but Octave does not fail in this case (and does nothing).
Added a test on the first output of fileparts, if this output is empty
we do not try to change the current directory.
2014-10-23 11:08:26 +02:00
Stéphane Adjemian (Karaba)
5ab08ed8d3
Added missing semi colon.
2014-10-21 16:37:57 +02:00
Stéphane Adjemian (Karaba)
ca28a2b778
Fixed load_m_file_data_legacy.m.
...
An m file data was not loading if outside the current directory.
2014-10-21 16:05:34 +02:00
Stéphane Adjemian (Karaba)
63d3157267
Do not force the user to provide a clean m data file when using the legacy data interface.
...
Note that all the variables listed in varobs need to have the same
number of observations.
2014-10-20 17:28:35 +02:00
Stéphane Adjemian (Karaba)
f48566aeae
Fixed prior bounds (according to the doc in master branch).
...
* Second and third positional arguments after the name of the
estimated parameter in the estimated_params block are only
considered in the optimization stage (not in the MCMC)
* Do not store bounds in bayestopt_, because bounds do not always
reflect restrictions implied by prior shapes.
* prior_bounds routine returns a structure (with fields lb and ub)
instead of a matrix.
2014-10-20 16:18:54 +02:00
Stéphane Adjemian (Karaba)
fb14d24036
Do not truncate the plotted prior densities with the truncation
...
parameters used for optimization (second and third positional
arguments after the name of the estimated parameter in the
estimated_params block).
2014-10-16 15:27:40 +02:00
Stéphane Adjemian (Karaba)
2d61c39276
Cosmetic changes.
2014-10-16 15:25:51 +02:00
Johannes Pfeifer
db2ba6d887
Clarify message in test_for_deep_parameters_calibration.m
2014-10-15 13:42:47 +02:00
Johannes Pfeifer
2c01113e8c
Fix bug when calling non-Bayesian smoother after Bayesian estimation
...
Because xparam1 is used by the smoother, but xparam was set to the posterior mean, the non-Bayesian smoother results were based on the parameters at the mode, which are stored in xparam1.
2014-10-15 09:49:07 +02:00
Stéphane Adjemian (Karaba)
d423ae63a8
Set default value for last input argument of lyapunov_symm routine (debug flag).
2014-10-15 09:02:42 +02:00
Johannes Pfeifer
590c0985f8
Add missing run index to looped variable in resol.m
2014-10-13 20:10:57 +02:00
Stéphane Adjemian (Karaba)
935f74883d
Added unit tests for lyapunov_symm routine.
2014-10-13 17:42:53 +02:00
Stéphane Adjemian (Karaba)
97b63105a0
Add a parameter to the lyapunov_symm routine (debug mode).
2014-10-13 17:42:53 +02:00
Stéphane Adjemian (Karaba)
55808060cf
Removed useless input (complete commit 438a671c3873e5c4e1bb02a54080e930fbc11886).
2014-10-13 17:42:52 +02:00
Johannes Pfeifer
b90f3deed2
Bugfixes and improvements related to method 3 of lyapunov_symm.m
...
- the function was called with the wrong input argument for this case (Q instead of R*Q*R'), crashing with incompatible matrix dimensions
- the persistent variable X was not updated when the size of it changed, leading to crashes when estimation is followed by calls to DsgeSmoother.m where the state-space is different
- Also eliminates the printed output in lyapunov_symm.m that could not be turned off and clutters estimation
2014-10-13 17:42:52 +02:00
Stéphane Adjemian
573d276f1a
Merge pull request #739 from JohannesPfeifer/Cosmetic_changes
...
Cosmetic changes, documentation, and small bugfix
2014-10-13 13:39:19 +02:00
Johannes Pfeifer
96df3b0043
Cosmetic changes to error messages
...
(cherry picked from commit ffa424d9d88dcd534272b154a3d9848df861914b)
2014-10-13 13:05:46 +02:00
Stéphane Adjemian
78621c03ee
Merge pull request #742 from JohannesPfeifer/second_order_hessian_problems
...
Deal with NaN and Inf in Hessian of dynamic model
2014-10-13 12:49:38 +02:00
Johannes Pfeifer
de5875a75b
Fix bug still present in CutSample.m
...
#733 was faulty because it did not account for changes in the first line when more than 1 MH file was present. Now, FirstDraw really denotes the first draw (as opposed to the last draw as before). The subsequent computation of FirstMhFile is then also correct.
2014-10-12 11:33:55 +02:00
Stéphane Adjemian
6c112a2701
Merge pull request #743 from JohannesPfeifer/debug_info_estimation
...
Add check for NaN parameters to initial_estimation_checks.m
2014-10-10 22:30:12 +02:00
Stéphane Adjemian
06fbf2b2c5
Merge pull request #746 from JohannesPfeifer/rplot
...
Filter out empty oo_.endo_simul in rplot.m
2014-10-10 22:25:07 +02:00
Stéphane Adjemian (Charybdis)
df1e734106
Merge branch 'steady_debug'
2014-10-10 21:47:24 +02:00
Stéphane Adjemian (Charybdis)
f4922a8a27
Cosmetic changes.
2014-10-10 21:46:50 +02:00
Stéphane Adjemian
9e3edd6673
Merge pull request #748 from JohannesPfeifer/maxit
...
Change maxit default value and correct manual
2014-10-10 19:03:56 +02:00
Stéphane Adjemian
37d4cf7e35
Merge pull request #753 from JohannesPfeifer/MCMC_diag
...
Improve tractability of McMCDiagnostics_core.m by adding header and comm...
2014-10-10 18:46:30 +02:00
Houtan Bastani
f4f7a02fd7
Provisions for MATLAB 8.4 (R2014b)
2014-10-10 10:41:04 +02:00
Johannes Pfeifer
1d68ed8da6
Improve tractability of McMCDiagnostics_core.m by adding header and comments. Also uses more intuitive variable names
2014-10-09 10:57:28 +02:00
Johannes Pfeifer
3187c70b97
Add debugging info on initial values for steady state computation
2014-09-30 15:05:12 +02:00
Johannes Pfeifer
a9bb341b0a
Increase default maxit for steady and deterministic simulations
...
Judging from forum reports, the default fails too often. Closes #747
2014-09-30 11:47:58 +02:00
Michel Juillard
6bbfa2fa6d
removed 1e6 in expression forcing a non-singular Jacobian
2014-09-30 08:13:31 +02:00
Johannes Pfeifer
6a8c968411
Filter out empty oo_.endo_simul in rplot.m
2014-09-29 15:00:45 +02:00
Michel Juillard
fa3e77d163
fixing bug in handling options for lmmcp
2014-09-28 10:07:08 +02:00
Johannes Pfeifer
127b7b0221
Add check for NaN parameters to initial_estimation_checks.m
...
Provides important info to debug cryptic crashes in later routines. Mostly applies to cases where people run estimation without stoch_simul
2014-09-25 09:02:36 +02:00
Johannes Pfeifer
b43d52278d
Deal with NaN and Inf in Hessian of dynamic model
...
Checks for these cases in stochastic_solvers.m to prevent cryptic crashes in dll-files later on
2014-09-25 08:49:19 +02:00
Johannes Pfeifer
2d39fc62e2
Make sure the output arguments of dsge_likelihood.m are actually set
...
Before, trend_coeff and ys were sometimes returned as empty
2014-09-21 11:54:43 +02:00
Johannes Pfeifer
3e427020d6
Cosmetic changes in headers
2014-09-21 11:51:46 +02:00
Stéphane Adjemian (Charybdis)
e2fd82d403
Merge branch 'cut_sample'
2014-09-20 11:18:16 +02:00
Stéphane Adjemian (Charybdis)
cc80c8662c
Fixes ambiguity in the output of CutSample routine (second part of PR #733 ).
2014-09-20 11:17:57 +02:00
Stéphane Adjemian (Charybdis)
bfc9719f05
Fix bug in in CutSample.m that led to wrong number of draws for moment computation (first part of PR #733 )
...
FirstLine actually defined the last line. One needs to 1. Otherwise,
Draws in GetAllPosteriorDraws.m will be (NumberOfDraws+1)*nblck.
2014-09-20 11:16:50 +02:00
Stéphane Adjemian (Charybdis)
2e08025cac
Fixed typo (wrong condition for defining the integration weights and nodes).
2014-09-19 22:05:42 +02:00
Johannes Pfeifer
79c5e18bfe
Cosmetic changes
...
- Suppresses spurious output from dynare_estimation_1.m
- Removes unset output argument from dynare_estimation_init.m (which seems to be totally unused as it was not set at all and nobody reported any crashes)
- Corrects header of dynare_estimation_init.m
2014-09-19 16:20:43 +02:00
Johannes Pfeifer
08b598609e
Clarify ambiguous printout in internals function
...
"Overall acceptance rate" could be read as over all chains.
Also capitalizes the name Matlab
2014-09-16 20:44:18 +02:00
Jukka Heikkonen
79d0e269a7
cosmetic change
2014-09-12 15:40:47 +02:00
Marco Ratto
4729459970
Properly handle case when post_metropolis=0: here steady_state must be added to smoothed variables.
2014-09-12 15:35:00 +02:00
Jukka Heikkonen
55b6d0eb93
1) check for restricted or extened var list
...
2) allow proper working will all GSA type of sample: prior, MC, posterior
2014-09-12 14:49:25 +02:00
Johannes Pfeifer
8655df67a9
Clean up use of verbosity option
...
- in dr_block.m and ep_residuals.m the option was hardcoded and disabled
- for csminwel1.m, no verbosity option exists anymore, thus definitions preceeding calls to it were redundant as was the options_.osr.verbose
2014-09-12 10:33:37 +02:00
ferhat
beee1d2f82
Correct the test on the number of eigenvalues outside the unit circle: do the test on each block instead of at the global level
2014-09-11 18:19:31 +02:00
Stéphane Adjemian (Scylla)
576ed55dda
Merge branch optimizer_number_5.
2014-09-11 17:38:03 +02:00
Stéphane Adjemian (Scylla)
89fa0ae9b6
Fixed typo.
2014-09-11 17:33:42 +02:00
Stéphane Adjemian (Charybdis)
7e3114847d
Fix crash in Ramsey with more than 1 instrument and steady state file.
...
Vector ys is undefined.
2014-09-11 15:33:55 +02:00
Stéphane Adjemian (Charybdis)
ce97a27c9d
Cosmetic changes.
2014-09-10 17:49:33 +02:00
Johannes Pfeifer
308ce25031
Make sure that solve_algo=0 inherits options from options_.steady
...
Otherwise, MaxIter is hard-coded
(cherry picked from commit 2499f641ac2fab7ddf938263d0ee34f73765c4c8)
2014-09-10 17:49:33 +02:00
Johannes Pfeifer
caa6d5d93e
Fix display of MH-history if parameter names do not have same length
...
In this case, cell2mat fails, because the dimensions are not consistent. Using char() instead padds with spaces
(cherry picked from commit 47b1a2df74cf1f643ca913ab4ff6c2057e8b58cf)
2014-09-10 17:49:33 +02:00
Johannes Pfeifer
41d1533086
Add check that prevents datafile from having same name as mod-file
...
Otherwise, the generated m-file might be called as the datafile, leading to infinite loops. The check cannot be moved to makedataset because M_.fname is not available there.
2014-09-10 17:49:33 +02:00
Stéphane Adjemian (Charybdis)
27d54758be
Fixed typo.
2014-09-10 17:49:33 +02:00
Stéphane Adjemian (Charybdis)
6d42ec66d5
Account for error code 10 (Inf in Jacobian of the dynamic model) in likelihood functions.
2014-09-10 17:49:33 +02:00
Stéphane Adjemian (Scylla)
5500846280
Added option distribution_proposal (estimation, non linear filters).
2014-09-08 22:36:41 +02:00
Stéphane Adjemian (Scylla)
4c9be8a56a
Removed useless option.
2014-09-08 22:36:41 +02:00
Stéphane Adjemian (Scylla)
df19396acf
Added option proposal_approximation (estimation, non linear filters).
2014-09-08 22:36:41 +02:00
Stéphane Adjemian (Scylla)
9bfdeb30e2
Bug fixes.
2014-09-08 22:36:41 +02:00
Stéphane Adjemian (Scylla)
5e4b7d8d42
Added filter_algorithm (estimation command, sets the particle filter algorithm).
2014-09-08 22:36:41 +02:00
Stéphane Adjemian (Scylla)
bcad4f31f2
Added option resampling_method (estimation command, non linear filters).
2014-09-08 22:36:41 +02:00
Stéphane Adjemian (Scylla)
08c74b8f41
Added option resampling_threshold (estimation command, non linear filters).
2014-09-08 22:36:40 +02:00
Stéphane Adjemian (Scylla)
a6009908e4
Added option resampling (estimation command, non linear filters).
2014-09-08 22:36:40 +02:00