Johannes Pfeifer
90affdd775
Clarify the timing convention in dynare++
...
Closes #1244
2016-08-21 10:22:56 +02:00
Houtan Bastani
848d81eb84
Merge pull request #1238 from rattoma/gsa
...
Bug fixes for identification with ML
2016-06-27 23:45:05 +02:00
Stéphane Adjemian (Hermes)
c5f8fe7f85
Added integration test for {variables,parameters} partitioning.
2016-06-27 12:10:15 +02:00
Stéphane Adjemian (Hermes)
581198741f
Revert "Revert "preprocessor: allow for partitioning of variables along multiple dimensions""
...
This reverts commit b0e7f1cfd7
.
2016-06-24 17:38:54 +02:00
Stéphane Adjemian (Hermes)
fcaf457f35
Cosmetic change (code factorization).
2016-06-24 17:35:56 +02:00
Houtan Bastani
b0e7f1cfd7
Revert "preprocessor: allow for partitioning of variables along multiple dimensions"
...
This reverts commit 7a29f50d99
.
2016-06-23 15:59:35 +02:00
Houtan Bastani
7a29f50d99
preprocessor: allow for partitioning of variables along multiple dimensions
2016-06-23 15:36:42 +02:00
Marco Ratto
be758613f4
fixed bugs that prevented the computation of the asymptotic Hessian with ML.
2016-06-19 11:09:59 +02:00
Marco Ratto
25120e54f5
added check for singular values whose eigenvectors contains only ONE column
2016-06-19 11:08:37 +02:00
Michel Juillard
b75f333a7e
fixed snes_1.cc for petsc-3.7.2
2016-06-18 11:21:42 +02:00
Michel Juillard
5d1162d229
fixed bug in writeCCOutput
2016-06-18 11:21:42 +02:00
Stéphane Adjemian (Hermes)
25243712ba
Fixed bug on non linux platforms + Cosmetic changes.
...
The paths to mex files was wrong.
2016-06-17 22:02:34 +02:00
Johannes Pfeifer
e214ec2976
Allow for parameter_set=mle_mode in conditional_forecast
2016-06-17 00:21:08 +02:00
Johannes Pfeifer
1c420e6056
Allow for parameter_set=mle_mode in shock_decomposition
...
Required after writing results into oo_.mle_mode for ML estimation
2016-06-17 00:21:08 +02:00
Stéphane Adjemian (Hermes)
1dea10d478
Updated dynare_config wrt #c7e848948156fe8febca22276a77c9586c565d87
2016-06-17 00:16:06 +02:00
Stéphane Adjemian (Hermes)
af9b069830
Moved isoctave routine in base directory.
2016-06-17 00:04:00 +02:00
Stéphane Adjemian (Hermes)
d80f6d9a99
Minimize the number of calls to addpath.
...
These calls have a prohibitive cost...
2016-06-16 23:55:07 +02:00
Stéphane Adjemian
3ae44efbea
Merge pull request #1218 from rattoma/gsa
...
Allow Screening with neighborhood_width sampling.
2016-06-16 22:18:39 +02:00
Stéphane Adjemian (Lupi)
33d35bc3c5
Added quantile routine in missing.
...
This is missing if the stats toolbox is not available. Integration test
TeX/fs2000_corr_ME.mod was failing because of its absence.
2016-06-16 14:33:57 +02:00
Johannes Pfeifer
f86b0a5ad6
Make dyn_forecast.m account for trend_coeffs saving coefficients for all variables
2016-06-16 12:05:38 +02:00
Johannes Pfeifer
3b09ab5424
Save Smoother.Trend and Smoother.Constant after MCMC
2016-06-16 12:05:38 +02:00
Johannes Pfeifer
1c84ccdc34
Save trend and constant for all variables in smoother
2016-06-16 12:05:38 +02:00
Johannes Pfeifer
3efe283bf0
Make oo_.Smoother.TrendCoeff have size of endogenous variables
...
Sets coefficients with unspecified trends to 0, allowing to later use the trend_var command for setting trends
2016-06-16 12:05:38 +02:00
Johannes Pfeifer
5d6d1336ef
Enable filter_covariance option in posterior sampling
2016-06-16 12:05:38 +02:00
Stéphane Adjemian (Hermes)
65ae97d37d
Fixed bug.
...
For uniform priors use the prior mean when computing the prior
moments (prior mode is not defined).
2016-06-16 11:59:47 +02:00
Stéphane Adjemian (Hermes)
789f21257e
Avoid side effects on globals (prior CLI and write_latex_prior_table commands).
2016-06-16 11:57:16 +02:00
Stéphane Adjemian (Hermes)
2c074d7cd2
Check that a prior is defined in prior CLI command
...
Behaviour consistent with the logic introduced in commit
64d01a806e
.
2016-06-16 11:16:23 +02:00
Stéphane Adjemian (Hermes)
a91e4dec75
Bug fixes.
...
Introduced when we increased the size of the mat files saved on
disk (see commit #e2942662479f822cd4ca1251158f0b5037c3a446).
2016-06-16 11:15:22 +02:00
Stéphane Adjemian (Hermes)
64d01a806e
Fixed behaviour of write_latex_prior_table command
2016-06-16 10:38:40 +02:00
Stéphane Adjemian (Lupi)
b70fe62503
Minor change in user reference manual.
...
The write_latex_prior_table has not to follow the estimation command but
the estimated_params block.
2016-06-15 17:15:53 +02:00
Johannes Pfeifer
e94a698a9b
Implement write_latex_prior_table.m
...
Fixes and replaces write_table_prior.m and uses consistent name. Also includes documentation
2016-06-15 16:47:39 +02:00
Stéphane Adjemian (Lupi)
fcb738616c
Fixed bug in extened_path_mc.
...
Wrong calling sequence to the routine defining the shocks.
2016-06-15 16:01:08 +02:00
Stéphane Adjemian (Lupi)
8b8db6bf38
Updated tests/Makefile clean rule.
...
Ensure tha we remove all tex, aux, log and eps generated files.
2016-06-15 14:39:38 +02:00
Stéphane Adjemian (Lupi)
c9d3db7db2
Changed optimization algorithm in integration test.
...
mode_compute=9 fails to find a mode with a positive definite hessian
matrix, swithed to mode_compute=8 (Dynare's implementation of the
simplex algorithm).
2016-06-15 14:19:43 +02:00
Stéphane Adjemian (Lupi)
1e7fc89e8d
Replaced filesep by hard coded slash.
...
See 57501f802e
.
2016-06-15 13:14:55 +02:00
Stéphane Adjemian (Lupi)
57501f802e
Revert "Cosmetic change."
...
This reverts commit 544da84e73
.
On Windows filesep returns a backslash ('\') as expected but
LaTeX, even on Windows, only understands slashes ('/') when
defining paths (for graphic or file inclusion).
2016-06-15 13:07:59 +02:00
Stéphane Adjemian (Lupi)
019223f7d6
Removed one (failing) integration test.
...
fs2000/fs2000_analytical_derivation.mod was almost a duplicate of
analytical_derivates/fs2000_analytical_derivation.mod.
The removed integration test was failing because of the sign of the
hessian matrix. The only significant difference between the two mod
files, was that the removed one did not use the closed form expression
of the steady state.
2016-06-15 12:53:48 +02:00
Stéphane Adjemian (Hermes)
473d335851
Fixed bug (wrong structure names).
2016-06-15 00:35:40 +02:00
Johannes Pfeifer
029e9495ba
Fix bug in dsge_var_likelihood.m where constant was not considered for dof when Gamma function was computed
...
Does not affect the maximum of the posterior as it only affects constant term
2016-06-15 00:30:28 +02:00
Johannes Pfeifer
4486d098b5
Save dsge_var objects at the mode
2016-06-15 00:30:28 +02:00
Johannes Pfeifer
2cf882fec5
Remove comments on dynare_estimation_1.m after implementing store_smoother_results
2016-06-15 00:30:28 +02:00
Johannes Pfeifer
d08fd37986
Do not set oo_.posterior.optimization-fields when mh_posterior_mode_estimation is used
2016-06-15 00:30:28 +02:00
Johannes Pfeifer
22a205d59a
Speed up fs2000_analytic_derivation.mod unit test by using previous mode-file
2016-06-15 00:30:28 +02:00
Johannes Pfeifer
1f433f0c97
Expand fs2000_5.mod unit test to second Hessian computation method
2016-06-15 00:30:28 +02:00
Johannes Pfeifer
552a9b5230
Fix bugs previously introduces in dynare_estimation_1.m related to penalty function
2016-06-15 00:30:28 +02:00
Johannes Pfeifer
2446ab02ba
Transform persistent variables of newrat.m into function arguments
2016-06-15 00:30:28 +02:00
Johannes Pfeifer
0c00e28799
Remove objective_function_penalty_base
2016-06-15 00:30:28 +02:00
Johannes Pfeifer
329b91d717
Harmonize output of objective functions
...
Closes #1149
Mirrors 1ad8df4635
2016-06-15 00:30:28 +02:00
Johannes Pfeifer
0edd8e2025
Add penalty_hessian.m and penalty_objective_function.m
2016-06-15 00:30:28 +02:00
Stéphane Adjemian (Hermes)
544da84e73
Cosmetic change.
...
Systematically use filesep instead of '/'.
2016-06-14 22:49:01 +02:00