2012年6月16日更新的Dynare4.3.0版（亲测可用）

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

[backcolor=rgba(255, 255, 255, 0.917969)]Dynare 4.3.0 版发布了
[backcolor=rgba(255, 255, 255, 0.917969)]新功能如下：
[backcolor=rgba(255, 255, 255, 0.917969)]Here is the list of the main user-visible changes:
[backcolor=rgba(255, 255, 255, 0.917969)]* New major algorithms:
[backcolor=rgba(255, 255, 255, 0.917969)]- Nonlinear estimation with a particle filter based on a second order
[backcolor=rgba(255, 255, 255, 0.917969)]  approximation of the model, as in Fernández-Villaverde and Rubio-Ramírez
[backcolor=rgba(255, 255, 255, 0.917969)]  (2005); this is triggered by setting `order=2' in the `estimation' command
[backcolor=rgba(255, 255, 255, 0.917969)]- Extended path solution method as in Fair and Taylor (1983); see the
[backcolor=rgba(255, 255, 255, 0.917969)]  `extended_path' command
[backcolor=rgba(255, 255, 255, 0.917969)]- Support for Markov-Switching Structural Bayesian VARs (MS-SBVAR) along the
[backcolor=rgba(255, 255, 255, 0.917969)]  lines of Sims, Waggoner and Zha (2008) (see the dedicated section in the
[backcolor=rgba(255, 255, 255, 0.917969)]  reference manual)
[backcolor=rgba(255, 255, 255, 0.917969)]- Optimal policy under discretion along the lines of Dennis (2007); see the
[backcolor=rgba(255, 255, 255, 0.917969)]  `discretionary_policy' command
[backcolor=rgba(255, 255, 255, 0.917969)]- Identification analysis along the lines of Iskrev (2010); see the
[backcolor=rgba(255, 255, 255, 0.917969)]  `identification' command
[backcolor=rgba(255, 255, 255, 0.917969)]- The Global Sensitivity Analysis toolbox (Ratto, 2008) is now part of the
[backcolor=rgba(255, 255, 255, 0.917969)]  official Dynare distribution

[backcolor=rgba(255, 255, 255, 0.917969)]* Other algorithmic improvements:
[backcolor=rgba(255, 255, 255, 0.917969)]- Stochastic simulation and estimation can benefit from block decomposition
[backcolor=rgba(255, 255, 255, 0.917969)]  (with the `block' option of `model'; only at 1st order)
[backcolor=rgba(255, 255, 255, 0.917969)]- Possibility of running smoother and filter on a calibrated model; see the
[backcolor=rgba(255, 255, 255, 0.917969)]  `calib_smoother' command
[backcolor=rgba(255, 255, 255, 0.917969)]- Possibility of doing conditional forecast on a calibrated model; see the
[backcolor=rgba(255, 255, 255, 0.917969)]  `parameter_set=calibration' option of the `conditional_forecast' command
[backcolor=rgba(255, 255, 255, 0.917969)]- The default algorithm for deterministic simulations has changed and is now
[backcolor=rgba(255, 255, 255, 0.917969)]  based on sparse matrices; the historical algorithm (Laffargue, Boucekkine
[backcolor=rgba(255, 255, 255, 0.917969)]  and Juillard) is still available under the `stack_solve_algo=6'option of the
[backcolor=rgba(255, 255, 255, 0.917969)]  `simul' command
[backcolor=rgba(255, 255, 255, 0.917969)]- Possibility of using an analytic gradient for the estimation; see the
[backcolor=rgba(255, 255, 255, 0.917969)]  `analytic_derivation' option of the `estimation' command
[backcolor=rgba(255, 255, 255, 0.917969)]- Implementation of the Nelder-Mead simplex based optimization routine for
[backcolor=rgba(255, 255, 255, 0.917969)]  computing the posterior mode; available under the `mode_compute=8' option of
[backcolor=rgba(255, 255, 255, 0.917969)]  the `estimation' command
[backcolor=rgba(255, 255, 255, 0.917969)]- Implementation of the CMA Evolution Strategy algorithm for computing the
[backcolor=rgba(255, 255, 255, 0.917969)]  posterior mode; available under the `mode_compute=9' option of the
[backcolor=rgba(255, 255, 255, 0.917969)]  `estimation' command
[backcolor=rgba(255, 255, 255, 0.917969)]- New solvers for Lyapunov equations which can accelerate the estimation of
[backcolor=rgba(255, 255, 255, 0.917969)]  large models; see the `lyapunov' option of the `estimation' command
[backcolor=rgba(255, 255, 255, 0.917969)]- New solvers for Sylvester equations which can accelerate the resolution of
[backcolor=rgba(255, 255, 255, 0.917969)]  large models with block decomposition; see the `sylvester' option of the
[backcolor=rgba(255, 255, 255, 0.917969)]  `stoch_simul' and `estimation' commands
[backcolor=rgba(255, 255, 255, 0.917969)]- The `ramsey_policy' command now displays the planner objective value
[backcolor=rgba(255, 255, 255, 0.917969)]  function under Ramsey policy and stores it in `oo_.planner_objective_value'
[backcolor=rgba(255, 255, 255, 0.917969)]- Theoretical autocovariances are now computed when the `block' option is
[backcolor=rgba(255, 255, 255, 0.917969)]  present
[backcolor=rgba(255, 255, 255, 0.917969)]- The `linear' option is now compatible with the `block' and `bytecode'
[backcolor=rgba(255, 255, 255, 0.917969)]  options
[backcolor=rgba(255, 255, 255, 0.917969)]- The `loglinear' option now works with purely backward or forward models at
[backcolor=rgba(255, 255, 255, 0.917969)]  first order

[backcolor=rgba(255, 255, 255, 0.917969)]

本帖隐藏的内容

dynare-4.3.0-win.rar (11.29 MB, 需要: 5 个论坛币) 本附件包括：

• dynare-4.3.0-win.exe

2012-6-16 04:01:48 上传

需要: 5 个论坛币  [购买]

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：dynare ARE Improvements Optimization distribution filter solution setting Taylor

* New features in the user interface:
- New mathematical primitives allowed in model block: `abs()', `sign()'
- The behavior with respect to graphs has changed:
   + By default, Dynare now displays graphs and saves them to disk in EPS
     format only
   + The format can be changed to PDF or FIG with the new `graph_format'
     option
   + It is possible to save graphs to disk without displaying them with the
     new `nodisplay' option
- New `nocheck' option to the `steady' command: tells not to check the steady
  state and accept values given by the user (useful for models with unit
  roots)

- A series of deterministic shocks can be passed as a pre-defined vector in
  the `values' statement of a `shocks' block

- New option `sub_draws' in the `estimation' command for controlling the
  number of draws used in computing the posterior distributions of various
  objects

- New macroprocessor command `@#ifdef' for testing if a macro-variable is
  defined

- New option `irf_shocks' of the `stoch_simul' command, to allow IRFs to be
  created only for certain exogenous variables

- In the parallel engine, possibility of assigning different weights to nodes
  in the cluster and of creating clusters comprised of nodes with different
  operating systems (see the relevant section in the reference manual)

- It is now possible to redefine a parameter in the `steady_state_model' block
  (use with caution)

- New option `maxit' in the `simul' and `steady' commands to determine the
  maximum number of iterations of the nonlinear solver

- New option `homotopy_force_continue' in the `steady' command to control the
  behavior when a homotopy fails

- Possibility of globally altering the defaults of options by providing a file
  in the `GlobalInitFile' field of the configuration file (use with caution)

- New option `nolog' to the `dynare' command line to avoid creating a logfile

- New option `-D' to the `dynare' command line with for defining
  macro-variables

* Miscellaneous changes:

- The `use_dll' option of `model' now creates a MEX file for the static model
  in addition to that for the dynamic model

- The `unit_root_vars' command is now obsolete; use the `diffuse_filter'
  option of the `estimation' command instead

- New option `--burn' to Dynare++ to discard initial simulation points

- New top-level MATLAB/Octave command `internals' for internal documentation
  and unitary tests


* Bugs and problems identified in version 4.2.5 and that have been fixed in
version 4.3.0:

- Backward models with the `loglinear' option were incorrectly handled

- Solving for hyperparameters of inverse gamma priors was sometimes crashing

- The deterministic solver for purely forward models was broken

- When running `estimation' or `identification' on models with non-diagonal
  structural error covariance matrices, while not simultaneously estimating
  the correlation between shocks (i.e. calibrating the correlation), the
  off-diagonal elements were incorrectly handled or crashes were occuring

- When using the `prefilter' option, smoother plots were omitting the smoothed
  observables

- In the rare case of entering and expression x as x^(alpha-1) with x being 0
  in steady state and alpha being a parameter equal to 2, the Jacobian was
  evaluating to 0 instead of 1

- Setting the prior for shock correlations was failing if a lower bound was not
  explicitly specified

先睹为快

是什么东东？

好东西哦啊，学习了

好东西哦啊，学习了

2012年6月16日更新的Dynare4.3.0版

谢谢

xiexiexiexie