Stéphane Adjemian (Charybdis)
4d51f38bd2
Added the possibility to use the cyclic reduction algorithm without the block option.
2012-07-11 18:26:22 +02:00
Stéphane Adjemian (Charybdis)
b02c83a926
Added unitary test.
...
Comparison of the solutions returned by the cyclic reduction and logarithmic reduction algorithm. Note
that in the case considered here the logarithmic reduction algorithm is faster.
2012-07-11 18:26:22 +02:00
Stéphane Adjemian (Charybdis)
56339bb3cf
Added logarithmic reduction algorithm to solve quadratic matrix equation.
...
This algorithm is a slower alternative to the cyclic reduction algorithm (useful for testing purpose).
2012-07-11 18:26:22 +02:00
Stéphane Adjemian (Charybdis)
47e543409c
Added texinfo header.
2012-07-11 18:26:22 +02:00
Stéphane Adjemian (Charybdis)
a86a904823
Cosmetic changes.
2012-07-11 18:26:22 +02:00
Stéphane Adjemian (Charybdis)
b4c60eeebf
Efficiency changes.
2012-07-11 18:26:22 +02:00
Stéphane Adjemian (Charybdis)
877cc55e78
Fixed bug.
2012-07-11 18:26:22 +02:00
Stéphane Adjemian (Charybdis)
38b493dacc
Changed copyright date.
2012-07-11 18:26:22 +02:00
Sébastien Villemot
3414d4d468
Fix crash in estimation introduced in 1fb89a07
2012-07-06 09:50:30 +02:00
Marco Ratto
40e1e60fd1
1) changed options of optimizer n. 1 with analytic derivs;
...
2) force no analytic derivative with mode_check;
2012-07-05 10:22:36 +02:00
Marco Ratto
ed4d37341c
Fix problem with models where steadystate files change parameter values.
...
1) allow to compute derivatives starting from NUMERICAL derivatives of jacobian and steady state: this has a minor cost in accuracy and allow apply without errors identification and estimation with numerical derivatives;
2) added trap in dynare_estimation_init: if steadystate changes param values, automaticly shifts to numerical derivs of jacoban and steady state + analytic derivatives of all the rest;
3) bug fixes for 2nd order derivatives w.r.t. model parameters;
2012-07-05 10:14:10 +02:00
Stéphane Adjemian (Charybdis)
379972d715
Removed prior_penalty in dsge_likelihood.
...
If options_.prior_trunc is set to zero (the default is strictly positive) then prior_correction is infinite because the prior density is zero (this is not true for the uniform prior)... This does not help the optimizer. Even if we do not fall in this case (because options_.prior_trunc>0 or becuase only uniform priors are used for the bounded parameters) the meaning of this correction is unclear.
2012-07-04 13:04:49 +02:00
Stéphane Adjemian (Charybdis)
a05b9d6a8a
Removed globals from simult.
2012-07-03 11:29:18 +02:00
Stéphane Adjemian (Charybdis)
1fb89a07e9
Removed global from set_state_space.
2012-07-03 11:29:18 +02:00
Stéphane Adjemian (Charybdis)
fcd016dc25
Removed global from check_model routine.
2012-07-03 11:29:18 +02:00
Marco Ratto
99c35e22f1
- Added trap to avoid infinite loops when type is not 'prior';
...
- Recover value of nosaddle from _core routine (bug fix when type is 'prior');
2012-07-02 10:55:02 +02:00
Marco Ratto
4cba20f231
Fixed bug in parallel_test
2012-07-02 10:15:38 +02:00
Ferhat Mihoubi
307d5d5d6a
Initializes the s variable
2012-07-01 15:19:36 +02:00
Ferhat Mihoubi
4488357f59
Adds the cycle reduction algorithm to solve the polynomial equation for retrieving the coefficients
...
associated to the endogenous variables in the decision rule.
2012-07-01 15:19:10 +02:00
Marco Ratto
bd9af2fa5a
Fixed bug reported by Rob Luginbuhl in dynare forum
2012-06-29 00:50:54 +02:00
Marco Ratto
a74f7c0285
Reduce the number of plots produced by default with rmse filtering and redform filtering
2012-06-29 00:48:24 +02:00
Marco Ratto
2510454bd1
Add missing figures when filtering is applied
2012-06-29 00:36:22 +02:00
Marco Ratto
3307b4b70e
Use Sobol sequence with seed = 1 (to avoid [0 0 0 0 0 ... ] point )
2012-06-29 00:36:02 +02:00
Sébastien Villemot
d44ca7296e
Merge remote-tracking branch 'ratto/master'
2012-06-22 10:57:25 +02:00
Michel Juillard
a6648b59ed
function evaluater_steady_state_file returns full size steady state
...
vector (including auxiliary variables) even in case of error flag in
evaluating steady state
2012-06-21 18:16:49 +02:00
Marco Ratto
cb2526ba52
Fixed bug introduced in commit a070f5cb26
.
...
The name npar was already used for the subsample loop.
To keep notation more in line with dynare options_ the old npar is renamed to B.
2012-06-21 17:13:00 +02:00
Sébastien Villemot
a7bddead43
Merge remote-tracking branch 'ratto/master'
2012-06-20 09:42:43 +02:00
Michel Juillard
2fa433f18e
fixing bug for estimation of models with measurement errors and
...
missing observations
2012-06-19 16:35:44 +02:00
Marco Ratto
0e1f60b29f
This should fix the bug originating random crash of sensitivity test routine
2012-06-19 15:33:41 +02:00
Marco Ratto
a5abdb3ce2
Fixed use of old figure syntax to dyn_figure
2012-06-19 15:32:42 +02:00
Michel Juillard
540fb1be48
fixing bug in discretionary_policy and implementing option solve_maxit
2012-06-19 14:08:45 +02:00
Michel Juillard
1eef328de0
correcting bug in welfare computation when using ramsey_policy and
...
histval
2012-06-18 20:29:35 +02:00
Stéphane Adjemian (Charybdis)
9c5bbd5c09
Added a routine to simulate a backward looking stochastic model with arbitrary precision (needed for PEA).
2012-06-18 14:59:52 +02:00
Stéphane Adjemian (Charybdis)
a18b071770
Fixed shocks decomposition bug.
...
(cherry picked from commit 68e7a310eda20f8f7611521ac45608a6941b31cc)
2012-06-18 14:55:36 +02:00
Houtan Bastani
328cc78d76
ms-sbvar: check for existence of mex file in dynare_config
2012-06-15 16:37:04 +02:00
Sébastien Villemot
9187e8ad4d
Typos
2012-06-15 15:09:39 +02:00
Marco Ratto
98c809c54e
Further on nograph: moved printed output when advanced=1 from plot_identification to disp_identification.
2012-06-15 13:45:26 +02:00
Marco Ratto
fd24b93667
fixes around options nograph and nodisplay
2012-06-15 13:07:26 +02:00
Marco Ratto
0494b92ed3
Proper handling of nograph option in gsa routines. Accordingly some more printed output on command window is allowed.
2012-06-15 12:29:22 +02:00
Marco Ratto
65cfa00e55
bug fix: lots of new empty figures were generated
...
(cherry picked from commit 335db3d8dabb3a429dbe85a8d0a2ba3c6d447991)
2012-06-14 18:55:06 +02:00
Stéphane Adjemian (Charybdis)
abad13d020
Kill estimation if the likelihood is complex or NaN.
2012-06-14 15:32:15 +02:00
Stéphane Adjemian (Charybdis)
1763855225
Consider the effective number of structural innovations in initial_estimation_checks routine. Some of the declared structural innovations may have been calibrated with a zero variance.
2012-06-14 15:32:15 +02:00
Stéphane Adjemian (Charybdis)
b907e82e7b
Removed NaNs in M_.Correlation_matrix if they are the consequence of variances (of structural innovations) calibrated to zero.
2012-06-14 15:32:14 +02:00
Michel Juillard
a5d84a90c3
fixing bug in initialization of bayestopt_.name
2012-06-14 13:04:51 +02:00
Michel Juillard
8f4fb2f16f
fixed welfare evaluation for arbirtrary value of the state
...
variables. The preprocessor still needs to be modified to allow
arbitrary initial value of the Lagrange multipliers
2012-06-13 21:00:38 +02:00
Michel Juillard
9f161ff339
fixing lower bound for priors on correlation coefficients
2012-06-13 15:55:01 +02:00
Michel Juillard
3ff832ddcc
added test for too large standard deviation in beta distribution;
...
cleaned up error messages related to priors; set error trap for
initilial likelihood Nan or complex
2012-06-13 15:47:01 +02:00
Michel Juillard
a39a0b3b67
fixed bug when only variances are estimated, but no deep parameter
2012-06-13 14:08:58 +02:00
Sébastien Villemot
661531ebff
Remove MATLAB short-circuit operators
...
They trigger warnings under Octave
2012-06-13 11:09:57 +02:00
Sébastien Villemot
8fe2eb23b9
New option simul_replic in preprocessor and documentation
2012-06-11 11:53:55 +02:00