3f48c8723a
Additional corrections related to the steady_state operator bug
2011-03-18 14:11:00 +01:00
32eff62af6
1) provisions for analytic scores and asymptotic Hessian provided by Nikolai Iskrev
...
2) several fixes and improvements in dynare_identification.m:
-) provide more info for strength of identification (relative to prior)
-) more drastic warning off
-) print info from ident_bruteforce.m
2011-03-18 11:05:40 +01:00
218b9efc34
identification: added brute force search for groups of parameters that replicate the derivative pattern of another parameter.
2011-03-18 11:00:20 +01:00
52cc078de5
skipped print of multicollinearity on the command window
2011-03-18 10:56:32 +01:00
179662baca
skipped useless call to initial checks when nargout>3.
2011-03-18 10:55:48 +01:00
8352873e06
Fixes to handle properly implicit derivation when STEADY_STATE syntax is applied
2011-03-18 10:54:09 +01:00
1ec1ea874a
Added utilities for analytic scores and asymptotic Hessian of likelihood.
...
Thanks to Nikolai Iskrev
2011-03-18 10:52:27 +01:00
31b6c08347
Correct a bug when the model contains deterministic exogenous variables and bytecode option is used.
...
Note that stochastic simulations do not work for the moment with block option.
2011-03-18 01:09:20 +01:00
0359c2801d
modifies alternative function for betapdf() for large values of a and b
2011-03-17 20:13:09 +01:00
7665b089fc
GSA: removed unused files
2011-03-17 16:54:55 +01:00
da867f1c93
GSA: add to MATLAB/Octave path
2011-03-17 16:29:18 +01:00
cde4f038d7
GSA: remove problematic statistics functions and replace them by calls to free ones
2011-03-17 16:14:12 +01:00
ebe28543fe
GSA: move stuff to the right place
2011-03-17 15:34:40 +01:00
8da2725f43
Corrections for steady_state operator bug with bytecode. lnsrch1_wrapper_one_boundary, omitted in the previous commit, is now corrected.
2011-03-16 09:59:40 +01:00
aac282d371
clean-up of commented lines in optimizer number 5;
...
eliminated globals and persistent from mr_gstep;
2011-03-15 15:27:41 +01:00
f48aa28e39
Corrections for steady_state operator bug with bytecode. bytecode is now fixed.
2011-03-14 17:46:00 +01:00
87e4125fa4
put *_params_derivs.m and identification code in conformity with additional steady state argument in *_dynamics.m
2011-03-14 11:40:40 +01:00
e029d46697
adding discretionary policy for linear quadratic models, thanks to code provided by Junior
2011-03-13 21:19:55 +01:00
55bb27c5f6
new correction for steady_state operator bug. Steady_state vector is passed as argument to *_dynamic model function. As a result, bytecode is currently broken.
2011-03-13 17:06:57 +01:00
dcfe3e5749
partly reverting changeset 9f7cfaec00 in order to correct problem in estimation: oo_.steady_state is not updated anymore in resol.m. (steady_state operator is broken in estimation).
2011-03-13 17:04:29 +01:00
96b7e1f599
corrected bug introduced in changeset 32c997f1ef of 02/25/11 and affecting k_order_perturbation
2011-03-13 17:01:10 +01:00
f70408e293
bug correction for dr.nspred when a variable is both backward and forward (bug introduced in changeset 32c997f1ef 02/25/11)
2011-03-10 11:18:41 +01:00
0c0b9abbd3
bug fixing for model_diagnostics
2011-03-09 14:44:24 +01:00
f7f100426d
bug fixing for mode_compute == 6
2011-03-09 14:43:28 +01:00
70a9c5e346
fixing bug for purely backward models (introduced in changeset 32c997f1ef, 02/25/11)
2011-03-09 13:45:59 +01:00
9f7cfaec00
fixing bug with steady_state operator
2011-03-09 13:43:17 +01:00
688366d6f2
SWZ: sz_prd correct calls to mex functions
2011-03-04 14:26:24 +01:00
d87484ec8e
Changes to markov file in ms-sbvar to work with new code
2011-03-01 11:25:53 -05:00
917b8e5285
Fixed bugs, clean-up and some more commenting of identification routines
2011-02-28 16:55:21 +01:00
84d7c97d4e
bug correction of previous change; further simplication in set_state_space
2011-02-27 22:03:43 +01:00
32c997f1ef
correcting bug when some variables don't appear at the current period
...
cleaning set_state_space.m, taking into account that all modesl have leads and lags on only one period.
2011-02-25 14:30:36 +01:00
b7133ebeb5
Fixed bugs related to global sensitivity analysis.
2011-02-25 09:27:33 +01:00
8001239118
Remove nonexistent smoother directory from addpath
2011-02-23 12:25:23 +01:00
86b88d4e70
one more smoother function removed
2011-02-23 11:24:16 +01:00
f553e69de3
removing unused Kalman smoother functions
2011-02-23 11:07:06 +01:00
e975336317
evaluate_smoother: fix call to DsgeSmoother (last argument was wrong)
2011-02-23 10:19:03 +01:00
dd6159d791
SWZ: remove instances of swz throughout
2011-02-22 15:06:38 +01:00
0db26e98a1
set correct permissions on file (remove execute)
2011-02-22 15:06:38 +01:00
c59133562c
more short-circuit logicals in the place of element-wise logicals
2011-02-22 15:06:38 +01:00
a153f81156
Partial information:
...
- fix various bugs
- do not fallback on full information in case of error, this is confusing
2011-02-22 14:46:24 +01:00
f6f96be0a0
Fix bug introduced in previous commit
2011-02-22 10:54:31 +01:00
8619ec7835
Fixed bug related to dname
2011-02-22 10:12:37 +01:00
39b73f73c5
Fixed compatibility problem with MATLAB <= 7.3
2011-02-21 12:05:48 +01:00
aafa328362
updating dynare_estimation_init.m and using it in dynare_estimation_1.m. Required for GSA.
2011-02-21 11:22:47 +01:00
c0d147c6da
corrected bug in conditional variance decomposition: removed reference to useless aux variable
2011-02-20 12:24:24 +01:00
8a0dabd07d
use || and && as opposed to | and & where appropriate
2011-02-16 15:14:38 +01:00
94ca528604
Merge remote branch 'ratto/master'
2011-02-14 14:29:39 +01:00
b41fde5088
changed swz paths to ms-sbvar
2011-02-14 12:26:38 +01:00
90e5f489b2
Then the last shock declared in M_.exo_names has zero variance or it has no effect on the model, there is a mismatch dimension, since the posteriorIRF provides a stock variable with less dimensions than M_.exo_nbr.
2011-02-14 12:01:38 +01:00
7fb471e9cc
Slightly simplified checks in computing gradient and Hessian for optimizer = 5.
2011-02-14 11:51:15 +01:00
13ea1c0046
A better way to compute outer product gradient (for optimizer 5) with the univariate Kalman Filter.
2011-02-14 11:48:29 +01:00
d0640ddf5f
Merge remote branch 'houtanb/master'
2011-02-10 19:20:56 +01:00
e5d9a7eb42
corrected bug for options_.kalman_tol and increased its default value to 1e-10
2011-02-10 18:48:08 +01:00
43479f6ef3
use short-circuit ops (|| and &&) as opposed to (| and &) to avoid warnings in Octave (and save time)
2011-02-10 15:54:23 +01:00
6f46019bfa
Fixed bug, where Ui,Vi,n0,np where not being initialized properly in exclusions.m identification for SWZ/MSBVAR
2011-02-09 09:25:22 -05:00
dc275f4af4
Moved the TeX file closing statement outside of loop, to fix a problem with non existant file id in producing TeX output in stoch_simul
2011-02-09 09:21:03 -05:00
eab7c1c6db
remove unused function
2011-02-09 10:06:13 +01:00
6ad29c9879
SWZ: fixing options vlistlog and vlistpercentage
2011-02-09 06:29:21 +01:00
b247c329d8
replaced expressions X == 0 by more efficient and robust isequal(X,0) when X is a matrix
...
porting earlier changes from DsgeLikelihood.m to DsgeLikelihood_hh.
cleaning code
2011-02-09 06:23:27 +01:00
f7477e23e5
fixed bug with parallel clusters with octave
2011-02-08 15:43:51 +01:00
7db0dad508
changed default for optimizer = 5
2011-02-08 15:42:38 +01:00
ad77ce7189
fixed echoes on command window
2011-02-08 15:41:17 +01:00
0ad3f11c20
Extensions for testing under octave
...
(cherry picked from commit f3a40a816314de603078151ccada2afdcbba2b22)
2011-02-07 21:16:50 +01:00
025db5c5f7
bug fixes for file exchange through the network under octave
2011-02-07 14:38:51 +01:00
12555b4320
Skip parallel plots under Octave
2011-02-07 14:34:10 +01:00
02652f6eb8
Updated copyright notices
2011-02-04 17:27:33 +01:00
757a9067c0
Global reindentation of MATLAB files
2011-02-04 17:17:48 +01:00
85332744d8
Ticket #59 : add cases for errors that were not being caught and convert AIM error codes so that they don't overlap with other error codes in print_info
2011-02-04 15:47:56 +01:00
9ae3115b9d
Fixing function name in header
2011-02-04 12:44:43 +01:00
e95defd117
Implement workaround for ticket #161
2011-02-04 11:55:54 +01:00
314c411d17
Fix matlab path of MS-SBVAR in config file
2011-02-04 11:55:31 +01:00
39adf099c3
SWZ: remove out of date code
2011-02-02 18:37:27 +01:00
06fe0c850a
SWZ: move mex code to new ms-sbvar dir and rename swz to ms-sbvar
2011-02-02 18:35:29 +01:00
0a93e9f28e
- warning of for octave;
...
- fixed bug with batch file for octave;
- fixed screen output for octave;
- cosmethics
2011-02-02 14:15:18 +01:00
bed32115d2
Fixes with screen output for parallel/octave + cosmethics
2011-02-02 14:13:11 +01:00
8111b671ff
Merge remote branch 'ratto/master'
2011-02-02 09:58:58 +01:00
6f184371ef
- Correction of temporary terms when bytecode is used and solve_algo <= 4
2011-02-02 00:31:37 +01:00
7583e0d3f1
semicolons
2011-02-01 23:37:41 +01:00
e7646a4412
disable warnings in octave + semicolon
2011-02-01 23:33:22 +01:00
45cf10ed11
missing semicolon
2011-02-01 23:32:36 +01:00
3eb1ec0c40
fixed bug in previous commit (~ispc)
2011-02-01 23:26:01 +01:00
062734895f
dynare provisions for rmdir under windows
2011-02-01 23:24:34 +01:00
9fdc7a655e
capture system command for mkdir also for linux
2011-02-01 23:21:49 +01:00
76644861a3
Provisions for octave under linux + small cosmethics.
2011-02-01 23:21:00 +01:00
92d44e4414
correction of the index of the state variables
2011-01-31 10:05:27 +01:00
8a128c9643
Temporary terms input argument is no more needed in dynare_solve_or_bytecode
2011-01-31 10:02:55 +01:00
41823ad10d
correction of the state variables list to display when the model is block decomposed
2011-01-31 10:01:08 +01:00
7fe6d73301
corrected bugs left in previous change set
2011-01-26 21:28:14 +01:00
f36247ceed
modifications to ramsey_policy code to allow for estimation
2011-01-26 21:24:47 +01:00
22d5bd16cf
removed useless auxiliary variables from call to kalman_transition_matrix()
2011-01-26 21:24:46 +01:00
bff8de837b
modifying dynare_resolve() calling sequence
2011-01-26 21:24:46 +01:00
a336799b96
corrected bug when mode_compute is a string
2011-01-26 21:24:46 +01:00
91e30d45f7
corrected bug related to ramsey_policy
2011-01-26 21:24:46 +01:00
55399a5dc5
Compatibility fix for Octave: under Octave, union() called on a column vector and a scalar returns a row vector, hence the need to add the 'rows' option
2011-01-24 15:34:02 -05:00
c71e0fbd6b
removing test about correlated data in initial checks before estimation: this condition is too restrictive.
2011-01-21 17:04:01 +01:00
f83d7db907
Fix of .mat extension with save for octave.
2011-01-21 11:28:28 +01:00
c5c99a80f6
Special fix for peculiar behavior of ls under octave/windows (+ use of ~ispc in place of isunix/ismac)
2011-01-21 11:26:24 +01:00
78c21916da
Fixed output for octave/unix octave/win
2011-01-21 11:25:30 +01:00
6c801be332
Removed catch ME instance for octave compatibility
2011-01-21 11:22:25 +01:00
4eb91731fc
Several fixes for octave compatibility:
...
- use of ispc;
- mat extension is save files;
- remove catch ME expressions;
- added printf message for octave runs
2011-01-21 11:21:32 +01:00
28a3b38cf4
For compatibility with octave (and for better coding) use of ~ispc in place of isunix/ismac
2011-01-21 11:18:29 +01:00
a3e4a7ff09
Eliminated annoying echoes on command window
2011-01-21 11:15:49 +01:00
1db24b3107
bug correction for diffuse smoother
2011-01-18 19:04:20 +01:00
c5310731d9
corrected bug affecting the smoother when called for a selected subset of variables
2011-01-18 19:04:20 +01:00
4cf358c895
Merge remote branch 'ferhat/master'
2011-01-18 17:24:42 +01:00
595675d333
Partial information changes that make adjustment for Octave and use rcond() < 1e-8 ..." to determine if a matrix is invertible plus some minor bug and formatting changes in dr1_PI.m
2011-01-17 20:40:41 +00:00
ce07223628
- The Temporary terms management with bytecode when the model is block decomposed and solve_algo<5 is now compatible with octave
...
- Gets rid of warning message during the compilation of bytecode
2011-01-14 19:24:18 +01:00
96b6f1bf05
- Corrects the following problem:
...
Octave BiCGStab algorithm involves a 0 division in case of a preconditioner equal to the LU decomposition of the A matrix (in a linear system of the form A.x = b).
- The solution:
Checks if the linear system is solved simply using: x_new = x_old + U \ (L \ x_old)
Ticket #11
2011-01-14 19:24:17 +01:00
708a062338
The Octave version of fsolve do not converge when it starts from the solution. Check if the initial guess is equal to the solution.
2011-01-14 19:24:17 +01:00
ac9415a943
- The bytecode.mex file has to be called when bytecode option is specified independently of the block option.
2011-01-14 10:39:34 +01:00
e2a1d77f6e
- added schur_statespace_transformation.m to factor it out of DsgeLikelihood.m and DsgeSmoother.m
...
and corrected a bug in the code
- added missing functions missing_DiffuseKalmanSmootherH1_Z.m (multivariate version) and
missing_DiffuseKalmanSmootherH3_Z.m (univariate version)
- use only these two versions of the Kalman smoother in DsgeSmoother.m
2011-01-13 21:50:26 +01:00
f7eb39f7bb
bug correction related to smoother
2011-01-13 21:45:09 +01:00
6ea053e47d
correcting bugs in diffuse Kalman smoother
2011-01-13 21:10:06 +01:00
2e0a36ae9f
Initialize estim_params_ in global_estimation.m. Necessary for smoothing models with no estimated parameters.
2011-01-13 21:10:06 +01:00
02fd6e668c
Add error message for non-implemented features of gamrnd.m
2011-01-13 12:28:44 +01:00
9e38d85053
Change the formula for empirical autocorrelations, so that the result always lies in [-1,1] (thanks to Johannes Pfeifer for pointing this)
2011-01-12 11:26:02 +01:00
17bc655159
Partial Information: Update with improved, generalised recursive PCL solution method
2011-01-11 21:57:57 +00:00
503b055df2
Fixed bugs in varlist_indices.m (thanks to Johannes Pfeifer for pointing them)
2011-01-10 13:11:25 +01:00
05b9c70ae8
removing command CALIB: it has not been working for a long time. Calibration is in fact a special case of method of moments and should be replaced by such a method.
2011-01-04 10:16:38 +01:00
256ff761e8
stochastic simulations: fix the number of generated data to be exactly options_.periods
...
added ./tests/simul
2011-01-02 16:55:15 +01:00
35765ee01c
- Matlab wrappers for the "print" option of bytecode
2010-12-31 17:03:19 +01:00
aab5b2a488
- Manages the temporary terms when the model is evaluated block by block
2010-12-31 16:22:24 +01:00
129303430e
The direction is not computed in same way in the dynamic case and in the static case
2010-12-31 16:20:35 +01:00
a882a25760
- length(args) is used instead of size(args, 2) to avoid to transpose column vectors
2010-12-31 16:16:29 +01:00
2dbeddd1a9
- Manages the temporary terms when the model is evaluated block by block
2010-12-31 16:00:49 +01:00
2707965da1
- extends the compatibility of dr1 with bytecode
2010-12-31 15:56:49 +01:00
7209f3638a
- consider a non sparse matrix for the Jacobian for compatibility reasons with dynare_solve
2010-12-31 15:53:28 +01:00
dcc46959b4
The default for options_.qz_criterium is now different for different contexts:
...
qz_criterium = 1+1e-6
- stoch_simul
- osr
- check
- dynare_estimation_1 with lik_init =2 or 3
qz_criterium = 1+1e-6 for dynare_estimation_1 with lik_init = 1
This correct a bug in estimation and computation of the posterior distribution of moments of endogenous variables when the priors permit roots too close to 1.
2010-12-23 08:34:13 +01:00
6bb8d41909
Revert "- added a test an a penalty in estimation (DsgeLikelihood.m) if, in a stationary model (lik_init==1), a particular parameter set generates unit roots."
...
There is a better way of dealing with occasional non-stationary models in estimation
This reverts commit 8c0fb55206
2010-12-22 09:40:39 +01:00
8c0fb55206
- added a test an a penalty in estimation (DsgeLikelihood.m) if, in a stationary model (lik_init==1), a particular parameter set generates unit roots.
...
- modified lyapunov_symm to return absolute value of unit roots in a third argument
2010-12-21 21:26:57 +01:00
ef56f87796
- fix for Octave printf
...
- missing semicolon
2010-12-20 15:55:46 +01:00
55e553f6dc
Missing semi-colons
2010-12-20 15:49:55 +01:00
ac0c0a935e
Cosmethics
2010-12-17 09:22:12 +01:00
b186eb7e84
Fixes for console mode in serial and parallel execution
2010-12-17 09:21:30 +01:00
191de78310
Introduced console mode monitoring of parallel runs;
...
Minor changes
2010-12-17 09:20:30 +01:00
916caf2e4b
Almost entirely rewritten:
...
1) got rid of recursive form;
2) better help
3) simplified structure and split between errors and warnings.
2010-12-17 09:16:30 +01:00
c2f0037e55
small addendum to help
2010-12-17 09:14:35 +01:00
d17faaf876
cosmethics
2010-12-17 09:12:54 +01:00
41c59778cd
For slave processes on the local machine, impose the same dynare path as the master.
2010-12-17 09:11:11 +01:00
c0cb3dd4fb
Compatibility fix for Octave: under Octave, union() called on a column vector and a scalar returns a row vector, hence the need to add the 'rows' option
2010-12-16 16:14:23 +01:00
b63590712c
fixed bug in argument number check and removed unused variable
2010-12-14 18:42:29 +01:00
e04a07c771
changed variable name to make clear that, for multinormal variables, we are using the Cholesky decomposition of the covariance matrix.
2010-12-11 18:09:01 +01:00
c1cb452e3d
correcting headers of all Kalman filter functions: returns MINUS loglikelihood
2010-12-10 22:31:30 +01:00
7a09356423
DsgeLikelihood.m header correction: the function returns MINUS log posterior
2010-12-10 22:28:06 +01:00
dfbd10a524
added choice of parameter set to shock_decomposition. This corrects a bug when shock_decomposition is requested after Metropolis iterations.
2010-12-08 13:02:59 +01:00
ea86e8cefc
adding function evaluate_smoother that calls DsgeSmoother with a given type of parameter set
2010-12-08 13:02:59 +01:00
9b166fdb08
NaN parameters warning: remove \n, it is not interpreted in a warning context (at least under Octave)
2010-12-08 11:32:45 +01:00
03fac30723
remove get_innovation_contemporaneous_impact.m that isn't called by the preprocessor or by any other function
2010-12-07 13:43:17 +01:00
3af62c4ac9
Fixed bug in resid.m (order matters in "or" statement, because of short-circuit: "ind" is not defined if "istag" is false)
2010-12-06 18:24:08 +01:00
0d1fd700c7
Posterior distribution of conditional variance decomposition: storing the steps chosen by the user in a separate field.
2010-12-05 10:47:31 +01:00
Ferhat Mihoubi
Marco Ratto
Michel Juillard
Sébastien Villemot
Houtan Bastani
Jacob Smith
Michel Juillard
George Perendia