September 2011 - Dev

[Trac] #201: implement adaptive Metropolis algorithm
by Trac Dynare 20 Apr '12

20 Apr '12

#201: implement adaptive Metropolis algorithm --------------------------+------------------------------------------------- Reporter: michel | Owner: michel Type: feature | Status: new Priority: major | Milestone: 5.0 Component: Core M-files | Version: Keywords: | --------------------------+------------------------------------------------- -- Ticket URL: <https://www.dynare.org/trac/ticket/201> Dynare <http://www.dynare.org> The Dynare project

1 3

[Trac] #63: new option instrument
by Trac Dynare 20 Apr '12

20 Apr '12

#63: new option instrument ---------------------------+------------------------------------------------ Reporter: michel | Owner: michel Type: enhancement | Status: new Priority: major | Milestone: Component: Documentation | Version: Keywords: | ---------------------------+------------------------------------------------ Document the new option "instrument" for ramsey_policy in reference manual and write wiki page on using *_steadystate.m file with ramsey_policy -- Ticket URL: <https://www.dynare.org/trac/ticket/63> Dynare <http://www.dynare.org> The Dynare project

1 4

[Trac] #198: update set_dynare_seed.m to use new function rng
by Trac Dynare 20 Apr '12

20 Apr '12

#198: update set_dynare_seed.m to use new function rng --------------------------+------------------------------------------------- Reporter: houtanb | Owner: houtanb Type: bug | Status: new Priority: minor | Milestone: 4.3 Component: Core M-files | Version: Keywords: | --------------------------+------------------------------------------------- NB: rng() introduced in Matlab R2011a -- Ticket URL: <https://www.dynare.org/trac/ticket/198> Dynare <http://www.dynare.org> The Dynare project

1 5

[Trac] #190: expectation operator conflicts with ramsey policy
by Trac Dynare 20 Apr '12

20 Apr '12

#190: expectation operator conflicts with ramsey policy --------------------------+------------------------------------------------- Reporter: michel | Owner: Type: bug | Status: new Priority: major | Milestone: Component: Core M-files | Version: Keywords: | --------------------------+------------------------------------------------- ramsey_policy does not provide the same results with expectation operator or if one adds the auxiliary variable/equation by hand I suspect that the auxiliary variables and the Lagrange mutlipliers are not entered in the right order or Ramsey policy fails if other auxiliary variables are already present in the model -- Ticket URL: <https://www.dynare.org/trac/ticket/190> Dynare <http://www.dynare.org> The Dynare project

1 2

[Trac] #161: Under Octave, gamma priors fail when variance is too small
by Trac Dynare 20 Apr '12

20 Apr '12

#161: Under Octave, gamma priors fail when variance is too small --------------------------+------------------------------------------------- Reporter: sebastien | Owner: Type: bug | Status: new Priority: major | Milestone: 4.2 Component: Core M-files | Version: 4.1.3 Keywords: | --------------------------+------------------------------------------------- This is reproducible on file RBC_Est.mod distributed with the user guide, which has two gamma priors. The problem is related to a bug in Octave: http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=493869 It may also affect beta priors which rely on gaminv() function. A minimal solution would be to give a sensible error message to the user, so that he knows he has to increase the variance. A better solution would be to reimplement gaminv. -- Ticket URL: <https://www.dynare.org/trac/ticket/161> Dynare <http://www.dynare.org> The Dynare project

1 2

[Trac] #177: mode_compute = 5 and dsge-var
by Trac Dynare 02 Apr '12

02 Apr '12

#177: mode_compute = 5 and dsge-var --------------------------+------------------------------------------------- Reporter: michel | Owner: Type: bug | Status: new Priority: major | Milestone: 4.3 Component: Core M-files | Version: Keywords: | --------------------------+------------------------------------------------- Paul McNelis reports that mode_compute=5 doesn't work with dsge-var estimation -- Ticket URL: <https://www.dynare.org/trac/ticket/177> Dynare <http://www.dynare.org> The Dynare project

2 4

[Trac] #206: MS-SBVAR: update irf, forecast and variance decomposition mex
by Trac Dynare 09 Mar '12

09 Mar '12

#206: MS-SBVAR: update irf, forecast and variance decomposition mex --------------------------+------------------------------------------------- Reporter: houtanb | Owner: Type: enhancement | Status: new Priority: major | Milestone: 4.3 Component: Core M-files | Version: Keywords: | --------------------------+------------------------------------------------- -- Ticket URL: <https://www.dynare.org/trac/ticket/206> Dynare <http://www.dynare.org> The Dynare project

1 3

[Trac] #173: fix license problems in GSA
by Trac Dynare 09 Jan '12

09 Jan '12

#173: fix license problems in GSA --------------------------+------------------------------------------------- Reporter: sebastien | Owner: Type: bug | Status: new Priority: critical | Milestone: Component: Core M-files | Version: Keywords: | --------------------------+------------------------------------------------- Some files in the {{{matlab/gsa}}} subdirectory have copyright status incompatible with inclusion in Dynare. At least: {{{ fdjac.m LPTAU.m optget.m Sampling_Function_2.m }}} Other files do not have any copyright notice, their status should be checked. The copyright status of the GSA manual is not explicited. Once these issues are fixed, the license.txt file should be updated accordingly. -- Ticket URL: <https://www.dynare.org/trac/ticket/173> Dynare <http://www.dynare.org> The Dynare project

1 5

[Trac] #157: histval + stoch_simul(periods=...) + forecast gives wrong result
by Trac Dynare 28 Dec '11

28 Dec '11

#157: histval + stoch_simul(periods=...) + forecast gives wrong result --------------------------+------------------------------------------------- Reporter: sebastien | Owner: Type: bug | Status: new Priority: major | Milestone: 4.2 Component: Core M-files | Version: 4.1.3 Keywords: | --------------------------+------------------------------------------------- If there is a histval block, followed by stoch_simul using empirical simulations ("periods" option), then the information provided by histval is lost (the "oo_.endo_simul" structure, which contains the histval information, is completely rewritten). A subsequent forecast command wrong results, since it will not use histval as starting point. -- Ticket URL: <https://www.dynare.org/trac/ticket/157> Dynare <http://www.dynare.org> The Dynare project

1 4

[Trac] #195: histval+stoch_simul
by Trac Dynare 21 Dec '11

21 Dec '11

#195: histval+stoch_simul --------------------------+------------------------------------------------- Reporter: stepan | Owner: houtanb Type: bug | Status: new Priority: critical | Milestone: 4.3 Component: Preprocessor | Version: Keywords: | --------------------------+------------------------------------------------- Contrary to what is explained in the documentation, the stochastic simulations are systematically initialized at the deterministic steady state. The histval block does not affect the way the simulations are initialized, and, worse, the preprocessor crashes if option periods is used (with an error message). The error message should be removed and the preprocessor should define a flag (options_.histval=1) whenever the block histval is used. -- Ticket URL: <https://www.dynare.org/trac/ticket/195> Dynare <http://www.dynare.org> The Dynare project

1 5