Commit Graph

7197 Commits (d7042b8e8071c4835f00803a3e8ac86380ed12bc)

Author SHA1 Message Date
Stéphane Adjemian (Charybdis) d7042b8e80 Fixes for models without parameters or exogenous variables. 2019-04-27 18:08:19 +02:00
Stéphane Adjemian (Charybdis) 1a55cd7945 Write files only if necessary.
DO not print files for parameters declaration, exogenous variables declarations
or parameter values if the selected equations do not have parameters and/or
exogenous variables (typically accounting identities).
2019-04-26 18:46:34 +02:00
Stéphane Adjemia (Scylla) 2d9e7a704b
Always write list of variables on more than one line.
(one line per variable)
2019-04-11 10:42:50 +02:00
Stéphane Adjemia (Scylla) fe4a15e417
Fixed bug if LHS no present in datablase.
Removed range on the left hand side.
2019-04-11 10:13:34 +02:00
Stéphane Adjemia (Scylla) ba46992e18
Bug fix (filter out lhs variable). 2019-04-10 10:40:41 +02:00
Stéphane Adjemia (Scylla) 8740355407
Rewrote evaluate routine.
- Can handle more than one equation.
 - Can handle identities.
 - Forbids dynamic equations.
 - Can handle following LHS y, diff(y), diff(diff(y)), log(y), diff(log(y)) and
   diff(diff(log(y))), other transformations will result in an error.
 - Added integration tests.

Remark 1. In the integration tests I compare the values returned by the
          evaluate routine with the values computed with the simulation
          routines. Normally the discrepancies should be small, but this is not
          the case when the endogenous variable appear under a log on the
          LHS. My current conclusion is that this has more to do with the
          cumulation of the accuracy errors in the simulation routine (a
          sequence of Newton algorithms) rather than with the evaluate routine.

Remark 2. Currently the only allowed nonlinear transformation on the LHS
          endogenous variable is the log. It is not difficult to generalise, at
          some point I had all the matlab functions allowed by Dynare,
          but this would complicate the code for not much gain.
2019-04-08 11:01:34 +02:00
Stéphane Adjemia (Scylla) de458022e5
Removed non existing subfolder from path. 2019-04-08 10:55:23 +02:00
Stéphane Adjemia (Scylla) 33c9b5f435
Cosmetic change.
Renamed the auxiliary variables for PAC/VAR expectations unrolled
expressions. Using shorter prefixes, PE_ and VE_ instead of pac_expectation and
var_expectations.
2019-04-02 22:57:45 +02:00
Stéphane Adjemia (Scylla) 8415ac48a0
Fixed bug (missing initialisation). 2019-04-02 21:31:45 +02:00
Stéphane Adjemia (Scylla) aa499671ce
Added the possibility to rename an endogenous variable in equation. 2019-04-02 18:06:47 +02:00
Stéphane Adjemia (Scylla) 599ebc2614
Ensure that residuals are removed even if the variable is not preceeded by a + symbol. 2019-04-02 15:40:43 +02:00
Stéphane Adjemia (Scylla) a72ee7e919
Updated dseries submodule. 2019-04-02 14:30:42 +02:00
Stéphane Adjemia (Scylla) f39f57b9b5
Added parameter values in cherrypick/agregate routines. 2019-04-02 07:11:32 +02:00
Stéphane Adjemian (Charybdis) 5a519b812f
Updated comments. 2019-03-29 17:52:46 +01:00
Stéphane Adjemian (Charybdis) 7b7bca8bda
Generalised trend component model.
Added the possibility to associate more than one trend to an endogenous
variable. The number of error correction equations is longer required to be
equal to the number of trends.
2019-03-29 17:52:46 +01:00
Houtan Bastani d84d8af8a8
dyn_ols: fix typo 2019-03-29 15:23:19 +01:00
Houtan Bastani 256949a243
fix spacing 2019-03-29 15:23:03 +01:00
Stéphane Adjemian (Charybdis) 39041009ef
Added tag on auxiliary variable for PAC/VAR expectations. 2019-03-28 11:19:38 +01:00
Stéphane Adjemian (Charybdis) cb97ed8081
Added tag on equation defining PAC/VAR expectation unrolled expression. 2019-03-28 11:18:42 +01:00
Stéphane Adjemian (Charybdis) 6c58598568
Fixed bug if lhs is an expression instead of an endogenous variable. 2019-03-27 15:24:05 +01:00
Houtan Bastani 825a010a90
sur, pooled_fgls, pooled_ols: add date range option 2019-03-27 14:57:57 +01:00
Houtan Bastani 4dbbf4f02e
olsgibbs: add date range option 2019-03-27 11:04:00 +01:00
Houtan Bastani d242ed88a2
dyn_ols: add date range option 2019-03-26 15:04:16 +01:00
Houtan Bastani ae6c118e9e
fix bug when looking for parameter in unary op node 2019-03-26 11:06:31 +01:00
Houtan Bastani 9ab4c6f80d
ols-style equations: handle additive elements separated by + and -
use same algorithm as in preprocessor to facilitate future changes
2019-03-26 11:06:30 +01:00
Stéphane Adjemian (Charybdis) b98e0a2bbf
Added routine to agregate cherry-picked submodels. 2019-03-25 17:59:22 +01:00
Stéphane Adjemian (Charybdis) d4a1d4b46a
Added missing aux. variable (PAC/VAR expectation). 2019-03-25 17:42:01 +01:00
Stéphane Adjemian (Charybdis) e20a3ffa45
Export tags on endogenous and exogenous variables. 2019-03-22 14:39:40 +01:00
Stéphane Adjemian (Charybdis) ecfafc048b
Export equation tags if defined in original mod file. 2019-03-22 11:29:59 +01:00
Stéphane Adjemian (Charybdis) 07a40d2df4
Do not unroll expectations in the equation where they are used...
... But create an auxiliary variable with corresponding equation (where the
expectation are unrolled). Also separate the growth neutrality correction.
2019-03-21 17:33:07 +01:00
Stéphane Adjemian (Charybdis) 567ca19000
Added routine to evaluate the RHS of an equation. 2019-03-19 07:08:55 +01:00
Houtan Bastani 62c4181394
common_parsing: update start/end dates when dates are supposed to overlap 2019-03-15 16:28:55 +01:00
Houtan Bastani 6150de2d4a
var_expectation: fix typo 2019-03-15 16:25:58 +01:00
Stéphane Adjemian (Charybdis) d3db092c81
Added a cherry-pick routine.
Extracts equations from a mod file and produce .inc files (equations, lists of
parameters, endogenous variables and exogenous variables) that can be included
in a mod file that will be used to simulate the model.

If an innovation has a tag `(used='estimationonly')` it will be excluded from
the generated files (ie list of shocks and equations).
2019-03-14 11:04:10 +01:00
Stéphane Adjemian (Charybdis) 52eed33c42
Fixed growth neutrality correction in presence of exogenous variables.
Also fixes growth neutrality correction in models with non optimizing
agents (correction was not taking into account the value of the share of non
optimizing agents).
2019-03-11 11:54:53 +01:00
Stéphane Adjemian (Charybdis) 6997e0a4a6
Added the possibility to have exogenous variables in the optimal part of PAC.
Works with iterative ols and nls.
2019-03-08 14:34:41 +01:00
Houtan Bastani d7246b3489
ols-style routines: allow user to specify parameters to be estimated 2019-03-08 11:15:33 +01:00
Stéphane Adjemian (Charybdis) 33e43a55b2
Cosmetic change. Print expression on more than one line (one line per additive term). 2019-03-08 09:36:56 +01:00
Houtan Bastani 183081f94b
pooled_fgls: remove useless part of code 2019-03-07 18:06:53 +01:00
Stéphane Adjemian (Charybdis) 03e60b6439
Cosmetic change. 2019-03-07 17:09:56 +01:00
Stéphane Adjemian (Charybdis) dac08da6a4
Added the possibility to tag a varexo variable as an observed variable. 2019-03-07 15:31:34 +01:00
Stéphane Adjemian (Charybdis) 1471b3bfce
Changegd estimator for the exogenous part of pac.estimation.iterative_ols routine. 2019-03-07 12:37:06 +01:00
Stéphane Adjemian (Charybdis) 4d69674874
Partially reverts 1190cab. 2019-03-07 12:31:23 +01:00
Houtan Bastani 1190caba61
pac.estimate.nls: clean up code: remove unused variables, unused output arguments, no need for otherwise in switch 2019-03-07 11:59:59 +01:00
Houtan Bastani b844bc53a0
pac: fix bugs in output of ec component 2019-03-07 11:44:40 +01:00
Stéphane Adjemian (Charybdis) 9eb64a0b64
Updated preprocessor submodule.
Fixes exogenous variables in PAC equation without non optimizing behaviour.
2019-03-06 15:39:00 +01:00
Houtan Bastani c0319a9bff
fix bug in printing of error message: ds is not available (or needed) in print function 2019-03-05 14:57:51 +01:00
Stéphane Adjemian (Charybdis) 4798c07ced
Avoid infinite loop in pac.estimation.iterative_ols(). 2019-03-05 07:21:08 +01:00
Houtan Bastani 01c5d2a90c
add model_name option to ols-style routines 2019-03-04 11:15:51 +01:00
Houtan Bastani e4888c0775
pooled_ols: use varargout instead of oo_ to pass values back to pooled_fgls 2019-03-04 11:15:51 +01:00