5d8d5e90d8
evaluate_smoother.m: pass updated M_.params and oo_ back to base workspace
...
Closes #1373
2017-03-17 13:15:39 +01:00
569de10511
Make sure block-decomposed model returns with correct error code if Inf or NaN is encountered
...
Missing from 5f85d3a200
2017-03-17 10:07:13 +01:00
ea13b12cf2
preprocessor: add lag info to equation cross references. closes #1398
2017-03-10 16:59:52 +01:00
33b38ab643
preprocessor: write error messages to cerr instead of cout, replace \n with endl
2017-03-01 12:44:31 +01:00
2d25858886
preprocessor: fix bug that caused temporary terms not to be printed for the parameter derivatives of the static model. closes #1397
2017-03-01 12:20:55 +01:00
0b52b778ed
preprocessor: for consistency, use equations.size() instead of equation_number() in classes that have equations as a field
2017-02-24 11:20:54 +01:00
39855c95d2
preprocessor: aesthetic fix
2017-02-10 12:47:43 +01:00
fabca90345
preprocessor: aesthetic fix
2017-02-09 16:23:42 +01:00
7ced4b5580
preprocessor: change error to warning because we don’t end processing in this situation; fix error message
2017-02-09 16:21:18 +01:00
edd2e98086
preprocessor: replace exit(1) with exit(EXIT_FAILURE)
2017-02-09 12:46:37 +01:00
9fbef0c107
Removed penalty_hessian routine.
...
+ Code factorization.
+ Added an option for using the penalized objective when computing numerically
the hessian at the mode.
Previous behaviour (introduced with penalty_hessian routine) was to compute the
hessian matrix at the mode with the penalized objective function (instead of
the original objective function). This behaviour hides problematic situations,
where the computed hessian (using the original objective) would not be full
rank. For instance, if the estimation ends up with a parameter on (or very
close to) the bounds of its possible values (which is often not a desirable
outcome), the estimated posterior variance would be zero for this
parameter (with the original objective) because the hessian is not finite in
this direction, while the posterior variance would be positive if the penalized
objective is used instead. But this estimate would not be reliable by
construction of the penalty which is quite ad-hoc (more fundamentally I do not
think that there exists any rational for approximating the covariance matrix
with the inverse of the hessian matrix if the mode is on the border of the set
of possible values).
This commit restore the behaviour previous to 2446ab02ba
2017-02-08 13:07:25 +00:00
5b6a888d7f
preprocessor: fix typo
2017-01-31 17:11:03 +01:00
f1d607af99
preprocessor: remove extra exogenous variables. closes #841
2017-01-27 22:48:17 +01:00
3a0b9a1143
preprocessor: don’t automatically declare external functions
2017-01-27 20:36:26 +01:00
3d4619fd85
preprocessor: handle undeclared external functions and lagged variables
2017-01-27 20:36:26 +01:00
cfae273038
keep track of all times an undeclared variable is encountered
2017-01-27 20:36:26 +01:00
bfd239aa26
preprocessor: issue warnings for undeclared model variables when the end of the model block is encountered. #1286
2017-01-27 20:36:26 +01:00
da31cca7d4
Fixed bug.
...
NO_POSTERIOR_KERNEL_DENSITY option was not modifying the expected field in
options_, consequently this option was no honored.
2017-01-20 17:35:43 +01:00
7fb7dd7ccc
fix nested parens for params derivatives. closes #1201
2017-01-05 18:19:37 +01:00
157369b505
when >32 nested parens encountered in matlab, print error message once per file in which such a situation occurred. #1201
2017-01-05 15:19:13 +01:00
b464226eaa
Merge pull request #1358 from JohannesPfeifer/nograph
...
Implement posterior_nograph option
2017-01-05 06:52:08 +01:00
09e7dde0ea
fix warnings introduced in 3b20d41a92 related to size_t/int comparison #1201
2017-01-02 11:38:13 +01:00
6bd1ff8e1c
3b20d41a92 used to_string from C++11 standard which breaks the snapshot build. #1201
2017-01-02 11:21:28 +01:00
952f545cd7
avoid unnecessary processing when a stream has 32 or fewer nested parenthesis. #1201
2016-12-30 18:32:20 +01:00
3b20d41a92
first iteration of fix for nested parenthesis in matlab. #1201
2016-12-30 18:14:08 +01:00
9582431bd5
bug fix: end preprocessing with error when more than 32 nested parenthesis are encountered. closes #1201
2016-12-28 14:02:50 +01:00
013043b1dd
ramsey_policy: accept all endogenous variables in var_list_, even auxiliary variables. closes #1355
2016-12-27 14:08:50 +01:00
452d3cd986
Implement preprocessor interface for posterior_nograph option
2016-12-26 13:07:46 +01:00
28d4ed1918
Finish implementation and documentation of nograph option of shock_decomposition.m
2016-12-26 12:52:28 +01:00
352786c2b4
load_mh_file: recompute results by default and load on request
...
Prevents general overwriting of results in oo_ and having stale results
2016-12-19 19:37:34 +01:00
5707b4d965
Make evaluate_smoother.m output former global variables for correct updating of these objects
2016-12-18 12:43:29 +01:00
2f717b5adc
Eliminate global variables from shock_decomposition.m
2016-12-18 09:57:51 +01:00
5515da191a
Add Raftery/Lewis (1992) convergence diagnostics
2016-12-17 17:22:05 +01:00
0f04a0f921
Geweke diagnostics: fix bug in interface that prevents setting the respective options
2016-12-17 17:22:05 +01:00
5334c7433d
Merge pull request #1345 from JohannesPfeifer/robust_lin_solve
...
robust_lin_solve: Fix mistakes introduced in 4b83c1bf763fe5029c94b7e5…
2016-12-17 17:18:19 +01:00
4a8e8db634
preprocessor: parallel: add NumberOfThreadsPerJob option. #1349
2016-12-13 11:35:37 +01:00
de7d239f7c
preprocessor: parallel: change default for singleCompThread. #1349
2016-12-13 11:12:04 +01:00
d5e20752ac
robust_lin_solve: Fix mistakes introduced in 4b83c1bf76
...
Interface was still missing and documentation of option was in wrong place in manual and wrong
2016-12-01 17:31:29 +01:00
5f85d3a200
block: fix bug introduced in e410043c24. #1245
2016-11-29 16:45:50 +01:00
e410043c24
block: add default argument for _dynamic functions: `varargout{1} = NaN;` #1245
2016-11-29 15:18:59 +01:00
7ec3dcc6e2
preprocessor: fix bug that caused all models declared linear to fail under ramsey. closes #419
2016-11-29 14:21:34 +01:00
3e9894028a
preprocessor: create field in M_ that is true when hessian is zero, false otherwise. closes #1335
2016-11-14 12:32:21 +01:00
31d2c7e332
Merge pull request #1324 from JohannesPfeifer/kalman
...
Three bugfixes for missing_DiffuseKalmanSmootherH1_Z.m that led to wrong results
2016-11-13 19:13:10 +01:00
2e54240dab
preprocessor: fix iterator types in ParsingDriver::svar()
2016-11-04 14:44:45 +01:00
98cf1bfc1d
Add smoothed state uncertainty to Kalman smoother routines
2016-11-04 09:23:55 +01:00
b069241d18
Merge pull request #1217 from JohannesPfeifer/qz_estimation
...
Make sure diffuse_filter triggers qz_criterium>1
2016-11-04 06:47:17 +01:00
09d374a0be
Merge pull request #1303 from JohannesPfeifer/shock_decomp
...
Shock decomposition and posterior moments
2016-11-04 00:41:04 +01:00
f087f84a25
preprocessor: define var for normcdf + msvc. #1259
2016-10-17 14:59:07 +02:00
4b2ddb6f1d
preprocessor: don’t need compiler argument to dynare when using octave. closes #1314
2016-10-14 17:35:10 +02:00
d564d832dd
preprocessor: add normcdf for MSVC. closes #1259
2016-10-14 16:11:44 +02:00
Johannes Pfeifer
Houtan Bastani
Stéphane Adjemian (Charybdis)
MichelJuillard