c829e7968d
If possible define boundaries for the share of optimizing agents in PAC/NLS.
...
The parameter is constrained to be in (0,1) for the following algorithms
- lsqnonlin (without Levenberg-Marquardt)
- fmincon
- annealing
- particleswarm
Other algorithms do not allow the definition of boundaries... We should add a
penality function to the objective for these algorithms.
2018-12-19 16:05:34 +01:00
df57bf7eb9
Fixed bug.
...
PAC/NLS routine was only working if the PAC model was named `pacman`.
2018-12-19 16:00:57 +01:00
11b24a0663
Add a constraint on the share of optimizing agents PAC/Iterative OLS.
...
Ensure that the parameter value lies betwwen 0 and 1.
2018-12-19 15:43:36 +01:00
c0570ff0af
Fixed typo.
2018-12-19 15:41:32 +01:00
23e37e45c4
Cosmetic change.
...
create a namespace for each {VAR/PAC} expectation model.
2018-12-19 11:43:26 +01:00
351da3b865
Do not update a dseries object, but instantiate a new object.
2018-12-19 10:53:09 +01:00
4775bca073
Fixed ordering of the columns of the Companion matrix...
...
For the level representation of the trend component model.
2018-12-14 17:37:35 +01:00
2cff485113
Fixed bug in the routine evaluating the (PAC/VAR) expectations.
2018-12-14 17:29:46 +01:00
38c8462142
If NLS, do not check the ordering of estimated parameters in PAC.
2018-12-12 16:28:19 +01:00
44e5a88ddd
dyn_ols: use AST instead of regex to parse equations
2018-12-07 19:54:32 +01:00
cb4384bb27
Create on the fly a routine for evaluating the (VAR/PAC) expectations.
...
The routine takes a dseries object as unique argument and return an updated
object with the expectation term.
If the mod file is named `example.mod` and if the (VAR/PAC) expectation model is
named `toto`, then after
var_expectation.print('toto');
the expectation term can be evaluated:
ts = example.var_expectations.evaluate_varexp(ts);
where ts is a dseries object containing all the time series appearign in the
auxiliary (var or trend_component).
2018-12-03 15:07:43 +01:00
53ab321de8
Added the possibility to use linear expressions in VAR_EXPECTATION_MODEL.
...
See tests/var-expectations/9/example.mod for a self documented example.
Also updated all the integration tests using the option `expression` instead of
`variable` (which is deprecated and will be removed at some point).
2018-11-30 23:36:06 +01:00
650c78f99d
Merge branch 'master' into ecb-master
2018-11-30 21:34:56 +01:00
d501d6d511
Added interface to lsqnonlin (Mathworks' optimization toolbox) in pac.estimate.nls.
2018-11-29 10:29:55 +01:00
c79be57447
Fixed definition of h (PAC expectation reduced form).
2018-11-27 10:05:40 +01:00
e6c716ae9b
Added the possibility to use Gauss-Newton in pac/nls.
...
Also added the computation of the covariance matrix of the NLS estimator (using
White and Domovitz approach) and integration test.
2018-11-26 09:53:18 +01:00
139c58dd76
Added Gauss Newton algorithm for minimizing sum of squared residuals.
2018-11-26 09:48:50 +01:00
efec664667
Preprocessor update + corresponding change in parameters derivatives
...
In the *_params_derivs.m files, in the "hp" matrix, the preprocessor now fully
outputs the symmetric elements, so getH needs to be adapted.
By the way, also clean up code for "rpp" and "gpp", were full symmetric
elements were also already present (and therefore do not need to be duplicated
in getH).
2018-11-22 17:53:39 +01:00
cf35496c06
Fixed bug in the evaluation of the sum of squared residuals (PAC/NLS).
2018-11-21 15:21:23 +01:00
7d2d0d6590
Added the possibility to estimate the share of optimizing agents by iterative OLS (PAC).
2018-11-21 15:07:15 +01:00
635aa65665
Merge branch 'ident_plot_bug' into 'master'
...
identification_analysis.m: Fix bug introduced in 60d95b65f2Dynare/dynare!1637
2018-11-16 16:21:14 +00:00
b615d2d795
identification_analysis.m: Fix bug introduced in 60d95b65f2
...
We already used a variable called offset
2018-11-16 16:20:27 +01:00
4ecbcbb136
evaluate_steady_state_file.m: Remove redundant setting of auxiliary variables
...
The original problems seems to have been fixed by #1133
Essentially reverts 3c7e60b744closes #1175
2018-11-16 14:12:55 +01:00
f947a31b80
evaluate_steady_state_file.m: fix two bugs in debugging mode
2018-11-16 09:24:43 +00:00
60d95b65f2
Identification strength: make plotting consistent
...
1. Rely on actually computed standard deviations in bayestopt_ instead of potentially unset estim_params_
2. Remove arbitrary normalizations/omitted normalization in case of division by 0 in normalization
3. Distinguish between 0 identification and division by 0 due to normalization in plots
(cherry picked from commit 7341e21a381850c47fbed018bf6a7acdda4fa92e)
2018-11-16 10:17:30 +01:00
ad451ad224
Merge branch 'prior_dens_info' into 'master'
...
Deal with info returned by priordens being a vector
See merge request Dynare/dynare!1629
2018-11-15 09:39:11 +00:00
513f3ec68e
Merge branch 'evaluate_steady_state' into 'master'
...
evaluate_steady_state.m: consistently use params
Closes #1627
See merge request Dynare/dynare!1630
2018-11-15 09:22:09 +00:00
30361ccb49
GSA scatter plots: Correctly pass LaTeX-names to figure
2018-11-14 18:37:54 +01:00
022913579a
map_calibration.m: Fix bug that prevented display of restrictions
2018-11-14 18:37:05 +01:00
c16c2fb894
evaluate_steady_state.m: consistently use params
...
Prevents erroneously relying on stale parameters from M.params (thanks to Tom Holden); closes #1627
2018-11-14 16:01:55 +01:00
09a166f4e7
Revert "adding missing any()"
...
This reverts commit a5b97a28a0
2018-11-14 15:04:27 +01:00
c1b0bb5ee3
initial_estimation_checks.m: Turn vector info into scalar
...
Related to a5b97a28a0
2018-11-14 15:02:15 +01:00
18faa9733c
Further updates related to minimal MATLAB version bump
2018-11-13 18:29:20 +01:00
7a75872f72
Modernization: use tilde (~) syntax for ignored output arguments
2018-11-13 18:02:09 +01:00
ce49cd95df
Add missing iscolumn and ismatrix for MATLAB < R2010b
...
Also fix a bug in isrow (it was not checking the rank of the array).
2018-11-13 16:59:27 +01:00
736d43c4e6
Bump minimal MATLAB version requirement to 7.9 (R2009b)
2018-11-13 15:59:16 +01:00
096936be9c
The preprocessor now compiles the MEX when use_dll is specified
...
Update documentation accordingly (except on macOS where the solution has not
yet been implemented).
Also include MinGW in the Windows installer.
2018-10-29 14:41:34 +01:00
cc4183d3a5
Fix for recent MATLABs under Windows
2018-10-26 15:02:26 +02:00
8cb51e26e6
options_.instruments is now a cell array
...
This fixes crashes under Octave (while MATLAB seems to accept array-indexing
with cell arrays).
2018-10-25 15:01:53 +02:00
dcea7514d9
Merge branch 'master' into ecb-master
2018-10-24 18:31:31 +02:00
8a2c38cf6c
olsgibbs: save fitted values in dataset; allow use of dictionary as in dyn_ols
2018-10-24 17:17:01 +02:00
510bc2e299
Removed unused variable.
2018-10-24 12:08:00 +02:00
1c1a3ea0a4
Removed tests on targets.
...
A target does not need to be a random walk. Also added a new integration
test (where the target is a constant, 0).
2018-10-24 12:06:14 +02:00
a53c63d6d5
Added routines to print PAC_EXPECTATION and VAR_EXPECTATION in files.
...
Each new routine pac.print() and var_expectation.print(), creates two files
that can be included (using the macro language) in a mod file. The first
file, {pac,var}expectationmodename-parameters.inc saved under
{M_.fname}/model/{pac,var}expectationmodel, contains the declaration of the
parameters created for the expanded (var or pac) expectation model, with
calibrated values. The second file, {pac,var}expectationmodename-parameters.inc
saved in the same subfolder, contains the expanded version of the (pac or var)
expectation term as a linear combination of the variables in the companion
representation of the expectatino model.
2018-10-14 16:57:51 +02:00
e5317b17de
Cosmetic change.
2018-10-06 17:52:58 +02:00
108854a484
Bug fix. verbosity option was not honoured in simplex algorithm (8).
...
Thanks to Reuben for reporting.
2018-10-06 17:50:37 +02:00
dfafe86246
Save teh posterior mean of the slope parameters as a column vector.
2018-10-06 16:55:42 +02:00
82187f9d41
Fixed olsgibbs routine.
2018-10-06 16:08:28 +02:00
798aaaa968
Cosmetic change.
2018-10-04 23:17:49 +02:00
ee2ad1ee15
olsgibbs: linear regression with Gibbs sampler
2018-10-04 17:12:47 +02:00
57bf291c00
add comment
2018-10-04 17:12:47 +02:00
ae71599292
Switch to new get_companion_matrix routine.
2018-09-28 19:27:17 +02:00
bbbaabc702
Cosmetic change.
2018-09-28 12:26:59 +02:00
3ad654b9b8
Allowing for different number of periods in conditional_forecast_path.
...
Updated preprocessor submodule.
2018-09-27 18:58:24 +02:00
07141a8681
Various optimizations.
2018-09-26 22:51:05 +02:00
7c83ba7ea7
Fixed documentation header.
2018-09-26 22:51:05 +02:00
973c3955f0
adjust for ‘targets’ keyword instead of ‘trends’
2018-09-25 14:58:36 +02:00
974bcd92ae
Merge branch 'ecb-master' into ecb-master-targets
2018-09-25 14:41:11 +02:00
c6d5b09c29
fix typo
2018-09-25 14:39:48 +02:00
b3a8062b46
Added missing output.
2018-09-19 17:39:58 +02:00
031e2c87c6
New version of get_companion_matrix + new integration test.
...
The routine is still buggy. In PAC and VAR_EXPECTATION models we
use get_companion_matrix_legacy routine instead.
2018-09-19 17:39:48 +02:00
2cf6ccdaa5
Updated dseries submodule.
2018-09-18 17:37:37 +02:00
3e6e448134
Updated dates and dseries submodules.
2018-09-14 23:13:13 +02:00
99aadf7d1a
Updated m-unit-tests submodule.
2018-09-14 15:37:30 +02:00
62301fa1e9
dyn_ols: fix typo
2018-09-14 15:09:31 +02:00
2518cd9884
Raise error of an optimization algorithm is not available.
2018-09-13 16:16:07 +02:00
2437d7034e
Give access to more than one optimizer in PAC estimation (NLS).
...
Default is to use csminwel optimizer (because it seems to do the job and does
not rely on the Mathworks toolbox).
2018-09-13 16:15:52 +02:00
eb316d7e2d
update files for change of option name from `trends` to `targets`
2018-09-13 12:24:32 +02:00
5ab8120780
get companion matrix using preprocessor output instead of get_ar_ec_matrices.m
2018-09-12 18:38:26 +02:00
74094683de
get_companion_matrix: fix header
2018-09-12 18:29:21 +02:00
a6150bae82
get_companion_matrix: simplify check (no need for allocation)
2018-09-12 18:29:14 +02:00
a32e2f165a
get_companion_matrix: remove unnecessary conditional
2018-09-12 18:29:07 +02:00
e9d7f6ca24
Merge branch 'master' into ecb-master
2018-09-12 18:28:47 +02:00
6815624a6a
Fixed bug.
...
Growth neutrality correction was applied twice.
2018-09-12 15:41:07 +02:00
51416bf2ae
Always use "isoctave" for testing Octave context
2018-09-07 17:22:08 +02:00
0f3678ec4a
Fixed ordering of variables in error correction term of PAC equation
...
PAC equation has to be written as
diff(x) = a0*(xstar(-1)-x(-1)) + a1*diff(x(-1)) + ... + ap*diff(x(-p)) + PAC_EXPECTATION(pacmodelname) + ...;
In the error correction term, a0*(xstar(-1)-x(-1)), we must have the difference
between the target (the trend xstar(-1)) and the level of the endogenous
variable (x(-1)). To ensure stability around the trend, the parameter a0 needs
to be positive.
REMARKS
[1] In the TREND_COMPONENT_MODEL the error correction terms are written in
reverse order, ie as the difference betwwen the level of the endogenous
variable and the trend variable.
[2] In the estimation routine we do not constrain a0 to be positive, but is
would surely help to satisfy this condition in the initial condition.
2018-09-06 22:07:31 +02:00
74ef4d2131
Cosmetic change.
2018-09-06 13:40:43 +02:00
5d8a1feda4
Fixed regular expression.
...
Data matrices were not correcty lagged for lags>1. This commit fixes the
inconsistencies (in terms of residuals) between Iterative OLS and NLS routines.
2018-09-06 13:40:27 +02:00
940c970ff3
Use same range in NLS and Iterative OLS.
...
The range option is the range of data considered for the right hand side variable.
2018-09-04 09:40:47 +02:00
6e1d06bddc
Display SSR in Iterative OLS.
2018-09-03 18:01:59 +02:00
8b1b1273c3
Fixed correction for growth neutrality.
...
Also added the possibility to use an endogenous variable for growth.
2018-09-03 17:57:10 +02:00
fde103d5f4
Removed debugging display.
2018-09-03 17:55:55 +02:00
a207550680
Fixed error correction term.
2018-09-03 17:53:01 +02:00
044f0f8de6
Added missing output required by some integration tests.
2018-09-03 17:38:09 +02:00
5ea0c8098b
Ensure that the ordering of the trend variables is consistent...
...
... With the ordering of the EC variables.
2018-09-03 17:35:59 +02:00
e1b2b80d64
Small efficiency change.
2018-08-29 17:42:49 +02:00
d23d1a470b
Added the possibility to estimate PAC_EQUATION with iterative ols and non constant growth.
2018-08-29 17:42:04 +02:00
30b34c4323
Small efficiency changes.
2018-08-29 16:15:52 +02:00
00498d19c8
Fixed ec matrix (rules out lag>1).
2018-08-28 19:25:05 +02:00
36388ce28a
Fixed bug in PAC_EXPECTATION.
...
The selection of the target variable in the error correction term was still
wrong if the target variable was not an auxiliary variable.
2018-08-28 19:23:35 +02:00
18a2626543
Fixed bugs in PAC_EXPECTATION.
...
- The selection of the target variable in the error correction term was wrong.
- Target variables in logs were still not working.
2018-08-28 12:12:21 +02:00
6dc35c676b
Fixed bug in VAR_EXPECTATION with TREND_COMPONENT_MODEL.
...
The selection of the expected variable in the companion VAR was not correct.
2018-08-28 11:06:20 +02:00
ae530293c5
Fixed bug. Trends in log where not accounted for in PAC equation.
2018-08-27 19:35:33 +02:00
83c9b0d5b6
Make rool for trend_component_model in var_expectation.
...
Not yet working, a bug in the preprocessor remains to be fixed. The
preprocessor does not create the correct number of reduced form parameters
for VAR_EXPECTATION when the auxiliary model is a trend component model,
because it ignores the fact that the model has to be rewritten in levels.
2018-08-27 14:37:26 +02:00
6ec9758313
update var_expectation code and tests for change in field name
2018-08-23 10:38:39 +02:00
cd05b9ba8f
Cosmetic changes.
2018-08-22 11:49:30 +02:00
2b6ee881a4
Efficiency changes.
2018-08-22 11:49:15 +02:00
442a70e905
Added missing semicolon.
2018-08-21 21:56:01 +02:00
4a0b3ffe7e
Adapted matlab code to new TREND_COMPONENT auxiliary model.
2018-08-21 21:49:58 +02:00
38b2593e31
Efficiency changes.
2018-08-21 21:02:20 +02:00
Stéphane Adjemia (Scylla)
Houtan Bastani
Sébastien Villemot
Johannes Pfeifer
Stéphane Adjemian (Charybdis)
Michel Juillard
Stéphane Adjemian(Charybdis)