Compare revisions

Sébastien Villemot · Sébastien Villemot · Houtan Bastani · Johannes Pfeifer · Sébastien Villemot · Johannes Pfeifer
--- a/NEWS
+++ b/NEWS
+Announcement for Dynare 4.4.0 (on 2013-12-11)
+=============================================
+We are pleased to announce the release of Dynare 4.4.0.
+This major release adds new features and fixes various bugs.
+The Windows package is already available for download. The Mac and
+Debian/Ubuntu packages should follow soon.
+All users are strongly encouraged to upgrade.
+This release is compatible with MATLAB versions ranging from 7.3 (R2006b) to
+8.2 (R2013b) and with GNU Octave version 3.6.
+Here is the list of major user-visible changes:
+* New major algorithms:
+ - Extended path at order 1 and above, also known as “stochastic extended
+   path”. This method is triggered by setting the `order' option of the
+   `extended_path' command to a value greater than 0. Dynare will then use a
+   Gaussian quadrature to take into account the effects of future uncertainty.
+   The time series for the endogenous variables are generated by assuming that
+   the agents believe that there will no more shocks after period t+order.
+ - Alternative algorithms for computing decision rules of a stochastic model,
+   based on the cycle reduction and logarithmic reduction algorithms. These
+   methods are respectively triggered by giving `dr = cycle_reduction' or 'dr
+   = logarithmic_reduction' as an option to the `stoch_simul' command.
+ - Pruning now works with 3rd order approximation, along the lines of
+   Andreasen, Fernández-Villaverde and Rubio-Ramírez (2013).
+ - Computation of conditional forecast using an extended path method. This is
+   triggered by the new option `simulation_type = deterministic' in the
+   `conditional_forecast' command. In this case, the `expectation' command in
+   the `conditional_forecast_paths' block has to be used to indicate the nature
+   of expectations (whether shocks are a surprise or are perfectly
+   anticipated).
+ - Endogenous priors as in Christiano, Trabandt and Walentin (2011). Those are
+   triggered by the new option `endogenous_prior' of the `estimation' command.
+* Other algorithmic improvements:
+ - New command `model_diagnostics' to perform various sanity checks on the
+   model. Note: in the past, some users may have used a preliminary MATLAB
+   function implementing this; the new command has the same syntax, except that
+   you shouldn't pass any argument to it.
+ - Terminal conditions of perfect foresight simulations can now be specified in
+   growth rates. More specifically, the new option `differentiate_forward_vars'
+   of the `model' block will create auxiliary forward looking variables
+   expressed in first differences or growth rates of the actual forward looking
+   variables defined in the model. These new variables have obvious zero
+   terminal conditions whatever the simulation context and this in many cases
+   helps convergence of simulations.
+ - Convergence diagnostics for single chain MCMC à la Geweke (1992, 1999).
+ - New optimizer for the posterior mode (triggered by `mode_compute=10'): it
+   uses the simpsa algorithm, based on the combination of the non-linear
+   simplex and simulated annealing algorithms and proposed by Cardoso, Salcedo
+   and Feyo de Azevedo (1996).
+ - The automatic detrending engine has been extended to work on models written
+   in logs. The corresponding trend variable type is `log_trend_var', and the
+   corresponding deflator type is `log_deflator'.
+* New features in the user interface:
+ - New set of functions for easily creating PDF reports including figures and
+   tables. See the “Reporting” section in the reference manual for more
+   details.
+ - New MATLAB/Octave classes for handling time series. See the “Time series”
+   section in the reference manual for more details.
+ - Datafiles in CSV format can now be used for estimation.
+ - New macro processor `length' operator, returns the length of an array.
+ - New option `all_values_required' of `initval' and `endval' blocks: enforces
+   initialization of all endogenous and exogenous variables within the block.
+ - Option `ar' can now be given to the `estimation' command.
+ - New options `nograph', `nointeractive' and `nowarn' to the `dynare' command,
+   for a better control of what is displayed.
+ - New option `nostrict' to the `dynare' command, for allowing Dynare to
+   continue processing when there are more endogenous variables than equations
+   or when an undeclared symbol is assigned in `initval' or `endval'.
+ - The information on MCMC acceptance rates, seeds, last log posterior
+   likelihood, and last parameter draw are now saved on the disk and can
+   be displayed with `internals --display-mh-history' or loaded into the
+   workspace with `internals --load-mh-history'.
+ - New options `mode_check_neighbourhood_size', `mode_check_symmetric_plots'
+   and `mode_check_number_of_points', for a better control of the diagnostic
+   plots.
+ - New option `parallel_local_files' of `model' block, for transferring extra
+   files during parallel computations.
+ - New option `clock' of `set_dynare_seed', for setting a different seed at
+   each run.
+ - New option `qz_zero_threshold' of the `check', `stoch_simul' and
+   `estimation' commands, for a better control of the situation where a
+   generalized eigenvalue is close to 0/0.
+ - New `verbatim' block for inclusion of text that should pass through the
+   preprocessor and be placed as is in the `modfile.m' file.
+ - New option `mcmc_jumping_covariance' of the `estimation' command, for a
+   better control of the covariance matrix used for the proposal density of the
+   MCMC sampler.
+ - New option `use_calibration' of the `estimated_params_init', for using the
+   calibration of deep parameters and the elements of the covariance matrix
+   specified in the `shocks' block as starting values for the estimation.
+ - New option `save_draws' of the `ms_simulation' command.
+ - New option `irf_plot_threshold' of the `stoch_simul' and `estimation'
+   commands, for a better control of the display of IRFs which are almost nil.
+ - New option `long_name' for endogenous, exogenous and parameter declarations,
+   which can be used to declare a long name for variables. That long name can
+   be programmatically retrieved in `M_.endo_names_long'.
+* Miscellaneous changes
+ - The deciles of some posterior moments were erroneously saved in a field
+   `Distribution' under `oo_'. This field is now called `deciles', for
+   consistency with other posterior moments and with the manual. Similarly, the
+   fields `Mean', `Median', `HPDsup', `HPDinf', and `Variance' are now
+   consistently capitalized.
+ - The console mode now implies the `nodisplay' option.
+* Bugs and problems identified in version 4.3.3 and that have been fixed in
+  version 4.4.0:
+ - In an `endval' block, auxiliary variables were not given the right value.
+   This would not result in wrong results, but could prevent convergence of
+   the steady state computation.
+ - Deterministic simulations with `stack_solve_algo=0' (the default value) were
+   crashing if some exogenous had a lag strictly greater than 1.
+ - When using the `mode_file' option, the initial estimation checks were not
+   performed for the loaded mode, but for the original starting values. Thus,
+   potential prior violations by the mode only appeared during estimation,
+   leading to potentially cryptic crashes and error messages.
+ - If a shock/measurement error variance was set to 0 in calibration, the
+   correlation matrix featured a 0 instead of a 1 on the diagonal, leading to
+   wrong estimation results.
+ - In the presence of calibrated covariances, estimation did not enforce
+   positive definiteness of the covariance matrix.
+ - Estimation using the `diffuse_filter' option together with the univariate
+   Kalman filter and a diagonal measurement error matrix was broken.
+ - A purely backward model with `k_order_solver' was leading to crashes of
+   MATLAB/Octave.
+ - Non-linear estimation was not skipping the specified presample when
+   computing the likelihood.
+ - IRFs and theoretical moments at order > 1 were broken for purely
+   forward-looking models.
+ - Simulated moments with constant variables was leading to crashes when
+   displaying autocorrelations.
+ - The `osr' command was sometimes crashing with cryptic error messages because
+   of some unaccounted error codes returned from a deeper routine.
+ - The check for stochastic singularity during initial estimation checks was
+   broken.
+ - Recursive estimation starting with the pathological case of `nobs=1' was
+   crashing.
+ - Conditional variance decomposition within or after estimation was crashing
+   when at least one shock had been calibrated to zero variance.
+ - The `estimated_params_init' and `estimated_params_bounds' blocks were broken
+   for correlations.
+ - The `filter_step_ahead' option was not producing any output in Bayesian
+   estimation.
+ - Deterministic simulations were sometimes erroneously indicating convergence
+   although the residuals were actually NaN or Inf.
+ - Supplying a user function in the `mode_compute' option was leading to
+   a crash.
+ - Deterministic simulation of models without any exogenous variable was
+   crashing.
+ - The MS-SBVAR code was not updating files between runs on Windows. This means
+   that if a MOD file was updated between runs in the same folder and a
+   `file_tag' was not changed, then the results would not change.
+ - The `ramsey_policy' command was not putting in `oo_.planner_objective_value'
+   the value of the planner objective at the optimum.
+* References:
+ - Andreasen, Martin M., Jesús Fernández-Villaverde, and Juan Rubio-Ramírez
+   (2013): “The Pruned State-Space System for Non-Linear DSGE Models: Theory
+   and Empirical Applications,” NBER Working Paper, 18983
+ - Cardoso, Margarida F., R. L. Salcedo and S. Feyo de Azevedo (1996): “The
+   simplex simulated annealing approach to continuous non-linear optimization,”
+   Computers chem. Engng, 20(9), 1065-1080
+ - Christiano, Lawrence J., Mathias Trabandt and Karl Walentin (2011):
+   “Introducing financial frictions and unemployment into a small open economy
+   model,” Journal of Economic Dynamics and Control, 35(12), 1999-2041
+ - Geweke, John (1992): “Evaluating the accuracy of sampling-based approaches
+   to the calculation of posterior moments,” in J.O. Berger, J.M. Bernardo,
+   A.P. Dawid, and A.F.M. Smith (eds.) Proceedings of the Fourth Valencia
+   International Meeting on Bayesian Statistics, pp. 169-194, Oxford University
+   Press
+ - Geweke, John (1999): “Using simulation methods for Bayesian econometric
+   models: Inference, development and communication,” Econometric Reviews,
+   18(1), 1-73
 Announcement for Dynare 4.3.3 (on 2013-04-12)
 =============================================

--- a/README.md
+++ b/README.md
@@ -78,9 +78,8 @@ If you have downloaded the sources from an official source archive or the source
 If you want to use Git, do the following from a terminal:
-    git clone http://github.com/DynareTeam/dynare.git
+    git clone --recursive http://github.com/DynareTeam/dynare.git
    cd dynare
-    git submodule update --init
    autoreconf -si
 The last line runs Autoconf and Automake in order to prepare the build environment (this is not necessary if you got the sources from an official source archive or the source snapshot).

--- a/configure.ac
+++ b/configure.ac
@@ -18,7 +18,7 @@ dnl You should have received a copy of the GNU General Public License
 dnl along with Dynare.  If not, see <http://www.gnu.org/licenses/>.
 AC_PREREQ([2.62])
-AC_INIT([dynare], [4.4-unstable])
+AC_INIT([dynare], [4.4.0])
 AC_CONFIG_SRCDIR([preprocessor/DynareMain.cc])
 AM_INIT_AUTOMAKE([1.11 -Wall -Wno-portability foreign no-dist-gzip dist-xz tar-pax])
@@ -83,10 +83,6 @@ CPPFLAGS="$CPPFLAGS_SAVED"
 # Don't use deprecated hash structures
 AC_DEFINE([BOOST_NO_HASH], [], [Don't use deprecated STL hash structures])
-# Check for dlopen(), needed by tests for estimation DLL
-AC_CHECK_LIB([dl], [dlopen], [LIBADD_DLOPEN="-ldl"], [])
-AC_SUBST([LIBADD_DLOPEN])
 # Check for libmatio, needed by Dynare++
 AX_MATIO
 AM_CONDITIONAL([HAVE_MATIO], [test "x$has_matio" = "xyes"])
@@ -192,10 +188,6 @@ AC_CONFIG_FILES([Makefile
                 dynare++/kord/Makefile
                 dynare++/src/Makefile
                 mex/sources/Makefile
-                 mex/sources/estimation/Makefile
-                 mex/sources/estimation/tests/Makefile
-                 mex/sources/estimation/libmat/Makefile
-                 mex/sources/estimation/libmat/tests/Makefile
 ])
 AC_ARG_ENABLE([matlab], AS_HELP_STRING([--disable-matlab], [disable compilation of MEX files for MATLAB]), [], [enable_matlab=yes])

--- a/switch_dw @ abb30501
+++ b/switch_dw @ abb30501
-Subproject commit 29c446f7fe8a773860ebee347662c4ae2494c5e9
+Subproject commit abb3050121bb92b63e665f697930cdf11fe018f5
--- a/utilities_dw @ 216abedb
+++ b/utilities_dw @ 216abedb
-Subproject commit b388d5eac8c8d092088db5ef805584ae4dd2d952
+Subproject commit 216abedb9ab4df5dd4dca07c721f7c07392801e9
--- a/doc/dynare.texi
+++ b/doc/dynare.texi
@@ -77,8 +77,6 @@
 @emph{Algorithms}
 @end macro
 @macro customhead{title}
 @iftex
 @sp 1
@@ -351,7 +349,7 @@ institutions who cannot afford, or do not want to pay for, MATLAB and
 are willing to bear the concomitant performance loss.
 The development of Dynare is mainly done at
-@uref{http://www.cepremap.ens.fr, Cepremap} by a core team of
+@uref{http://www.cepremap.fr, Cepremap} by a core team of
 researchers who devote part of their time to software development.
 Currently the development team of Dynare is composed of Stéphane
 Adjemian (Université du Maine, Gains and Cepremap), Houtan Bastani
@@ -1020,9 +1018,9 @@ extension or if the filename contains a non-alphanumeric character;
 Declarations of variables and parameters are made with the following commands:
-@deffn Command var @var{VARIABLE_NAME} [$@var{LATEX_NAME}$ [(long_name=@var{QUOTED_STRING})]]@dots{};
+@deffn Command var @var{VARIABLE_NAME} [$@var{LATEX_NAME}$] [(long_name=@var{QUOTED_STRING})]@dots{};
-@deffnx Command var (deflator = @var{MODEL_EXPRESSION}) @var{VARIABLE_NAME} [$@var{LATEX_NAME}$ [(long_name=@var{QUOTED_STRING})]]@dots{};
+@deffnx Command var (deflator = @var{MODEL_EXPRESSION}) @var{VARIABLE_NAME} [$@var{LATEX_NAME}$] [(long_name=@var{QUOTED_STRING})]@dots{};
-@deffnx Command var (log_deflator = @var{MODEL_EXPRESSION}) @var{VARIABLE_NAME} [$@var{LATEX_NAME}$ [(long_name=@var{QUOTED_STRING})]]@dots{};
+@deffnx Command var (log_deflator = @var{MODEL_EXPRESSION}) @var{VARIABLE_NAME} [$@var{LATEX_NAME}$] [(long_name=@var{QUOTED_STRING})]@dots{};
 @descriptionhead
@@ -1075,7 +1073,7 @@ var c $C$ (long_name=`Consumption');
 @end deffn
-@deffn Command varexo @var{VARIABLE_NAME} [$@var{LATEX_NAME}$ [(long_name=@var{QUOTED_STRING})]]@dots{};
+@deffn Command varexo @var{VARIABLE_NAME} [$@var{LATEX_NAME}$] [(long_name=@var{QUOTED_STRING})]@dots{};
 @descriptionhead
@@ -1103,7 +1101,7 @@ varexo m gov;
 @end deffn
-@deffn Command varexo_det @var{VARIABLE_NAME} [$@var{LATEX_NAME}$ [(long_name=@var{QUOTED_STRING})]]@dots{};
+@deffn Command varexo_det @var{VARIABLE_NAME} [$@var{LATEX_NAME}$] [(long_name=@var{QUOTED_STRING})]@dots{};
 @descriptionhead
@@ -1140,7 +1138,7 @@ varexo_det tau;
 @end deffn
-@deffn Command parameters @var{PARAMETER_NAME} [$@var{LATEX_NAME}$ [(long_name=@var{QUOTED_STRING})]]@dots{};
+@deffn Command parameters @var{PARAMETER_NAME} [$@var{LATEX_NAME}$] [(long_name=@var{QUOTED_STRING})]@dots{};
 @descriptionhead
@@ -2837,25 +2835,42 @@ steady(homotopy_mode = 1, homotopy_steps = 50);
 If you know how to compute the steady state for your model, you can
 provide a MATLAB/Octave function doing the computation instead of
-using @code{steady}. If your MOD-file is called
+using @code{steady}. Again, there are two options for doing that:
-@file{@var{FILENAME}.mod}, the steady state file should be called
-@file{@var{FILENAME}_steadystate.m}.
-Again, there are two options for creating this file:
 @itemize
 @item
-The easiest way is to write a @code{steady_state_model} block.
+The easiest way is to write a @code{steady_state_model} block, which
+is described below in more details. See also @file{fs2000.mod} in the
+@file{examples} directory for an example.
+The steady state file generated by Dynare will be called
+@file{@var{FILENAME}_steadystate2.m}.
 @item
-You can write the corresponding Matlab function by hand. See @file{fs2000_steadystate.m}
+You can write the corresponding MATLAB function by hand. If your
-in the @file{examples} directory for an example. This option
+MOD-file is called @file{@var{FILENAME}.mod}, the steady state file
-gives a bit more flexibility, at the expense of a heavier
+must be called @file{@var{FILENAME}_steadystate.m}. See
-programming burden and a lesser efficiency.
+@file{NK_baseline_steadystate.m} in the @file{examples} directory for
+an example. This option gives a bit more flexibility, at the expense
+of a heavier programming burden and a lesser efficiency.
 @end itemize
+Note that both files allow to update parameters in each call of 
+the function. This allows for example to calibrate a model to a labor 
+supply of 0.2 in steady state by setting the labor disutility parameter 
+to a corresponding value (see @file{NK_baseline_steadystate.m} in the 
+@file{examples} directory). They can also be used in estimation 
+where some parameter may be a function of an estimated parameter 
+and needs to be updated for every parameter draw. For example, one might
+ want to set the capital utilization cost parameter as a function 
+of the discount rate to ensure that capacity utilization is 1 in steady 
+state. Treating both parameters as independent or not updating one as 
+a function of the other would lead to wrong results. But this also means 
+that care is required. Do not accidentally overwrite your parameters 
+with new values as it will lead to wrong results.
 @anchor{steady_state_model}
 @deffn Block steady_state_model ;
@@ -3017,6 +3032,7 @@ must have full rank.
 @xref{solve_algo}, for the possible values and their meaning.
 @item qz_zero_threshold = @var{DOUBLE}
+@anchor{qz_zero_threshold}
 Value used to test if a generalized eigenvalue is 0/0 in the generalized
 Schur decomposition  (in which case  the model  does not admit  a unique
 solution). Default: @code{1e-6}.
@@ -3462,9 +3478,7 @@ problems. Default: @code{1.000001} (except when estimating with
 @code{0.999999} in that case; @pxref{Estimation}).
 @item qz_zero_threshold = @var{DOUBLE}
-Value used to test if a generalized eigenvalue is 0/0 in the generalized
+@xref{qz_zero_threshold}.
-Schur decomposition  (in which case  the model  does not admit  a unique
-solution). Default: @code{1e-6}.
 @item replic = @var{INTEGER}
 Number of simulated series used to compute the IRFs. Default: @code{1}
@@ -4250,7 +4264,7 @@ stderr VARIABLE_NAME | corr VARIABLE_NAME_1, VARIABLE_NAME_2 | PARAMETER_NAME
 @table @code
 @item use_calibration
-For not specifically intialized parameters, use the deep parameters and the elements of the covariance matrix specified in the @code{shocks}-block from calibration as starting values for estimation. For components of the @code{shocks}-block that were not explicitly specified during calibration or which violate the prior, the prior mean is used.
+For not specifically initialized parameters, use the deep parameters and the elements of the covariance matrix specified in the @code{shocks} block from calibration as starting values for estimation. For components of the @code{shocks} block that were not explicitly specified during calibration or which violate the prior, the prior mean is used.
 @end table
 @xref{estimated_params}, for the meaning and syntax of the various components.
@@ -4313,23 +4327,45 @@ acceptance ratio  should be close to  one third or one  quarter. If this
 not the case, you can stop the MCMC (@code{Ctrl-C}) and change the value
 of option @code{mh_jscale} (see below).
+Note that by default Dynare generates random numbers using the algorithm
+@code{mt199937ar} (@i{ie} Mersenne Twister method) with a seed set equal
+to @code{0}.   Consequently the MCMCs  in Dynare are  deterministic: one
+will  get  exactly  the  same   results  across  different  Dynare  runs
+(@i{ceteris paribus}).  For instance, the posterior moments or posterior
+densities  will be  exactly the  same. This  behaviour allows  to easily
+identify the  consequences of a change  on the model, the  priors or the
+estimation options. But one may also  want to check that across multiple
+runs, with  different sequences of  proposals, the returned  results are
+almost  identical. This  should  be  true if  the  number of  iterations
+(@i{ie} the value of @code{mh_replic}) is important enough to ensure the
+convergence of  the MCMC to its  ergodic distribution. In this  case the
+default behaviour of the random number generators in not wanted, and the
+user  should set  the  seed according  to the  system  clock before  the
+estimation command using the following command:
+@example
+set_dynare_seed('clock');
+@end example
+@noindent so that the sequence of proposals will be different across different runs.
 @algorithmshead
-The Monte Carlo Markov Chain (MCMC) diagnostics are generated
+The Monte  Carlo Markov  Chain (MCMC) diagnostics  are generated  by the
-by the estimation command if @ref{mh_replic} is larger than 2000 and if 
+estimation command if @ref{mh_replic} is  larger than 2000 and if option
-option @ref{nodiagnostic} is not used. If @ref{mh_nblocks} is equal to one,
+@ref{nodiagnostic} is not used. If @ref{mh_nblocks} is equal to one, the
-the convergence diagnostics of @cite{Geweke (1992,1999)} is computed. It uses a
+convergence diagnostics  of @cite{Geweke  (1992,1999)} is  computed.  It
-chi square test to compare the means of the first and last draws specified by
+uses a chi square test to compare  the means of the first and last draws
-@ref{geweke_interval} after discarding the burnin of @ref{mh_drop}. The test is
+specified  by  @ref{geweke_interval}  after  discarding  the  burnin  of
-computed using variance estimates under the assumption of no serial correlation
+@ref{mh_drop}. The test  is computed using variance  estimates under the
-as well as using tapering windows specified in @ref{taper_steps}.
+assumption of  no serial correlation  as well as using  tapering windows
-If @ref{mh_nblocks}  is larger  than 1, the convergence diagnostics of 
+specified in  @ref{taper_steps}.  If @ref{mh_nblocks} is  larger than 1,
-@cite{Brooks and Gelman (1998)} are used instead.
+the convergence diagnostics of @cite{Brooks  and Gelman (1998)} are used
-As described in section  3 of @cite{Brooks and Gelman (1998)} the univariate
+instead.  As described  in section 3 of @cite{Brooks  and Gelman (1998)}
-convergence diagnostics are  based on comparing pooled  and within MCMC moments 
+the univariate convergence diagnostics are based on comparing pooled and
-(Dynare displays the  second and third order  moments, and
+within MCMC moments (Dynare displays the second and third order moments,
-the length of  the Highest Probability Density interval  covering 80% of
+and the length of the  Highest Probability Density interval covering 80%
-the  posterior   distribution).   Due  to  computational   reasons,  the
+of  the  posterior distribution).   Due  to  computational reasons,  the
 multivariate  convergence diagnostic  does not  follow @cite{Brooks  and
 Gelman (1998)}  strictly, but rather  applies their idea  for univariate
 convergence  diagnostics  to  the  range  of  the  posterior  likelihood
@@ -4887,6 +4923,9 @@ Default value is @code{0}.
 forecast covariance matrices.
 @item filter_step_ahead = [@var{INTEGER1}:@var{INTEGER2}]
+See below.
+@item filter_step_ahead = [@var{INTEGER1} @var{INTEGER2}  @dots{}]
 @anchor{filter_step_ahead}
 @vindex oo_.FilteredVariablesKStepAhead
 @vindex oo_.FilteredVariablesKStepAheadVariances
@@ -5023,9 +5062,7 @@ the filter, but rather use a penalty value for the likelihood when
 such a singularity is encountered. Default: @code{1}.
 @item qz_zero_threshold = @var{DOUBLE}
-Value used to test if a generalized eigenvalue is 0/0 in the generalized
+@xref{qz_zero_threshold}.
-Schur decomposition  (in which case  the model  does not admit  a unique
-solution). Default: @code{1e-6}.
 @item taper_steps = [@var{INTEGER1} @var{INTEGER2} @dots{}]
 @anchor{taper_steps}
@@ -5149,7 +5186,7 @@ Variable set by the @code{estimation} command, if it is used with the
 @defvr {MATLAB/Octave variable} oo_.FilteredVariablesKStepAhead
 Variable set by the @code{estimation} command, if it is used with the
-@code{filter_step_ahead} option.
+@code{filter_step_ahead} option. The k-steps are stored along the rows while the columns indicate the respective variables. The third dimension of the array provides the observation for which the forecast has been made. For example, if @code{filter_step_ahead=[1 2 4]} and @code{nobs=200}, the element (3,5,204) stores the four period ahead filtered value of variable 5 computed at time t=200 for time t=204. The periods at the beginning and end of the sample for which no forecasts can be made, e.g. entries (1,5,1) and (1,5,204) in the example, are set to zero.  
 @end defvr
 @defvr {MATLAB/Octave variable} oo_.FilteredVariablesKStepAheadVariances
@@ -5157,6 +5194,16 @@ Variable set by the @code{estimation} command, if it is used with the
 @code{filter_step_ahead} option.
 @end defvr
+@defvr {MATLAB/Octave variable} oo_.Filtered_Variables_X_step_ahead
+Variable set by the @code{estimation} command, if it is used with the @code{filter_step_ahead} option in the context of Bayesian estimation. Fields are of the form:
+@example
+@code{oo_.Filtered_Variables_X_step_ahead.@var{VARIABLE_NAME}}
+@end example
+The nth entry stores the k-step ahead filtered variable computed at time n for time n+k.
+@end defvr
 @defvr {MATLAB/Octave variable} oo_.PosteriorIRF.dsge
 Variable set by the @code{estimation} command, if it is used with the
 @code{bayesian_irf} option. Fields are of the form:
@@ -5490,7 +5537,7 @@ option in @code{conditional_forecast} command set to @code{deterministic}.
 Because in this case deterministic simulations are carried out,
 the nature of the shocks (surprise or perfect foresight) has to be indicated
 in the @code{conditional_forecast_paths} block, using the command @code{expectation}
-for each endogenous path. The forecasts are plotted using the rplot command.
+for each endogenous path. The forecasts are plotted using the @code{rplot} command.
 Finally, it is possible to do forecasting with a Bayesian VAR using
 the @code{bvar_forecast} command.
@@ -6040,7 +6087,10 @@ This command declares the policy maker objective, for use with
 You need to give the one-period objective, not the discounted lifetime
 objective. The discount factor is given by the @code{planner_discount}
-option of @code{ramsey_policy} and @code{discretionary_policy}.
+option of @code{ramsey_policy} and @code{discretionary_policy}. The
+objective function can only contain current endogenous variables and no
+exogenous ones. This limitation is easily circumvented by defining an
+appropriate auxiliary variable in the model.
 With @code{ramsey_policy}, you are not limited to quadratic
 objectives: you can give any arbitrary nonlinear expression.
@@ -6924,11 +6974,14 @@ The first period of data (@i{i.e.} for quarterly data, an integer in
 [@code{1,4}]). Default: @code{1}
 @item final_year = @var{INTEGER}
-The last year of data. Default: Set to encompass entire dataset
+The last year of data. Default: Set to encompass entire dataset.
 @item final_subperiod = @var{INTEGER}
 The final period of data (@i{i.e.} for monthly data, an integer in
-[@code{1,12}]. Default: Set to encompass entire dataset
+[@code{1,12}]. Default: When final_year is also missing, set to
+encompass entire dataset; when final_year is indicated, set to the
+maximum number of subperiods given the frequency (@i{i.e}. 4 for
+quarterly data, 12 for monthly,...).
 @item datafile = @var{FILENAME}
 @xref{datafile}.
@@ -8096,6 +8149,12 @@ the one that is highest on the MATLAB/Octave path).
 @end deffn
+@deffn {MATLAB/Octave command} write_latex_definitions ;
+Writes the names, @LaTeX{} names and long names of model variables to
+tables in a file named @code{<<M_.fname>>_latex_definitions.tex}.
+@end deffn
 @node The Configuration File
@@ -8439,12 +8498,14 @@ using time series.
 Dynare  understands dates  in  a  mod file.  Users  can declare  annual,
 quaterly, monthly or weekly dates using the following syntax:
 @example
 1990Y
 1990Q3
 1990M11
 1990W49
 @end example
 @noindent Behind the scene, the dynare's preprocessor translates these expressions
 into instantiations of the  Matlab/Octave's class @dates described
 below. Basic  operations can be performed  on dates:
@@ -8507,6 +8568,33 @@ Tests if a @dates object follows another @dates object or is equal to this objec
 @noindent One can select an element, or some elements, in a @dates object as he would extract some elements from a vector in Matlab/Octave. Let @code{a = 1950Q1:1951Q1} be a @dates object, then @code{a(1)==1950Q1} returns @code{1}, @code{a(end)==1951Q1} returns @code{1} and @code{a(end-1:end)} selects the two last elements of @code{a} (by instantiating the @dates object @code{[1950Q4, 1951Q1]}).
+@remarkhead
+@noindent Dynare substitutes any occurence of dates in the mod file into an instantiation of the @dates class regardless of the context. For instance, @code{d = 1950Q1;} will be translated as @code{a = dates('1950Q1');}. This automatic substitution can lead to a crash if a date is defined in a string. Typically, if the user wants to display a date:
+@example
+disp('Initial period is 1950Q1');
+@end example
+@noindent Dynare will translate this as:
+@example
+disp('Initial period is dates('1950Q1')');
+@end example
+@noindent which will lead to a crash because this expression is illegal in Matlab. For this situation, Dynare provides the @code{$} escape parameter. The following expression:
+@example
+disp('Initial period is $1950Q1');
+@end example
+@noindent will be translated as:
+@example
+disp('Initial period is 1950Q1');
+@end example
+@noindent in the generated matlab script.
 @node dates class
 @subsection dates class
@@ -8528,7 +8616,9 @@ for monthly  dates and 1-52 for  weekly dates) are stored  in the second
 column.
 @end table
 @noindent Each member is private, one can display the content of a member but cannot change its value:
 @example
 >> d = dates('2009Q2');
 >> d.time
@@ -8548,13 +8638,17 @@ ans =
 @deftypefnx {dates} dates (@code{FREQ})
 Returns an empty @dates object with  a given frequency (if the constructor is called with one input argument).  @code{FREQ} is a character equal to 'Y' or 'A'  for annual dates, 'Q' for quaterly dates, 'M' for monthly dates or 'W'  for weekly dates. Note that @code{FREQ} is not  case sensitive,  so that,  for instance,  'q' is  also allowed  for quaterly dates. The frequency can also be set with an integer scalar equal to 1 (annual), 4 (quaterly), 12 (monthly) or 52 (weekly). The instantiation of empty objects can be used to rename  the @dates class. For  instance, if one  only works  with quaterly dates, he can create @code{qq} as:
 @example
 qq = dates('Q')
 @end example
-and a @dates object holding the date @code{2009Q2}:
+@noindent and a @dates object holding the date @code{2009Q2}:
 @example
 d0 = dates(2009,2);
 @end example
 @noindent which is much simpler if @dates objects have to be defined programatically.
 @end deftypefn
@@ -8568,7 +8662,6 @@ Returns a @dates object that represents a date as given by the string @code{STRI
 @end deftypefn
 @sp 1
 @deftypefn {dates} dates (@code{DATES})
@@ -8598,15 +8691,19 @@ do4 = dates('Q',1950, 1);
 @sp 1
-A list of the available methods, by alphabetical order, is given below. Note that the Matlab/Octave classes do not allow in place modifications: when a method is applied to an object a new object is instantiated. For instance, to apply the method @code{multiplybytwo} to an object @code{X} we write:
+@noindent A list of the available methods, by alphabetical order, is given below. Note that the Matlab/Octave classes do not allow in place modifications: when a method is applied to an object a new object is instantiated. For instance, to apply the method @code{multiplybytwo} to an object @code{X} we write:
 @example
 Y = X.multiplybytwo()
 @end example
-or equivalently:
+@noindent or equivalently:
 @example
 Y = multiplybytwo(X)
 @end example
-the object @code{X} is left unchanged, and the object @code{Y} is a modified copy of @code{X}.
+@noindent the object @code{X} is left unchanged, and the object @code{Y} is a modified copy of @code{X}.
 @sp 1
@@ -9070,7 +9167,7 @@ A @code{nobs} by @code{vobs} array of doubles, the data.
 @end table
-@noindent The following constructors are available:
+@noindent @code{freq}, @code{nobs}, @code{vobs}, @code{data}, @code{name}, @code{tex} are private members. The following constructors are available:
 @deftypefn  {dseries} dseries ()
 @deftypefnx {dseries} dseries (@var{INITIAL_DATE})
@@ -9100,9 +9197,9 @@ If a @file{.mat} file is used instead, it should provide the same informations.
 @sp 1
-@deftypefn {dseries} dseries (@var{DATA_MATRIX}, @var{INITIAL_DATE}, @var{LIST_OF_NAMES}, @var{LIST_OF_TEX_NAMES})
+@deftypefn {dseries} dseries (@var{DATA_MATRIX}[, @var{INITIAL_DATE}[, @var{LIST_OF_NAMES}[, @var{LIST_OF_TEX_NAMES}]]])
-If the data is not read from a file, it can be provided via a @math{T}x@math{N} matrix as the first argument to @code{dseries}' constructor, with @math{T} representing the number of observations on @math{N} variables. The second argument, @var{INITIAL_DATE}, can be either a @dates object representing the period of the first observation or a string which would be used to instantiate a @dates object. The third argument, @var{LIST_OF_NAMES}, is a @math{N} by @math{1} cell of strings  with one entry for each variable name. The final argument, @var{LIST_OF_TEX_NAMES}, is a @math{N} by @math{1} cell of strings composed of the @LaTeX{} names associated with the variables. Input arguments two, three and four are optional. The default value for @var{INITIAL_DATE} is @code{1Y}.
+If the data is not read from a file, it can be provided via a @math{T}x@math{N} matrix as the first argument to @code{dseries}' constructor, with @math{T} representing the number of observations on @math{N} variables. The optional second argument, @var{INITIAL_DATE}, can be either a @dates object representing the period of the first observation or a string which would be used to instantiate a @dates object. Its default value is @code{dates('1Y')}. The optional third argument, @var{LIST_OF_NAMES}, is a @math{N} by @math{1} cell of strings  with one entry for each variable name. The default name associated with column @code{i} of @var{DATA_MATRIX} is @code{Variable_i}. The final argument, @var{LIST_OF_TEX_NAMES}, is a @math{N} by @math{1} cell of strings composed of the @LaTeX{} names associated with the variables. The default @LaTeX{} name associated with column @code{i} of @var{DATA_MATRIX} is @code{Variable\_i}.
 @end deftypefn
@@ -9130,7 +9227,7 @@ do3 = dseries([1; 2; 3], 1999Q3, @{`var123'@}, @{`var_@{123@}'@});
 @sp 1
-A list of the available methods, by alphabetical order, is given below.
+@noindent A list of the available methods, by alphabetical order, is given below.
 @deftypefn {dseries} {[@var{A}, @var{B}] = } align (@var{A}, @var{B})
@@ -9172,7 +9269,7 @@ ts1 is a dseries object:
 @deftypefn {dseries} {@var{B} = } baxter_king_filter (@var{A}, @var{hf}, @var{lf}, @var{K})
-Implementation of Baxter and King (1999) band pass filter for @dseries objects. This filter isolates business cycle fluctuations with a period of length ranging between @var{hf} (high frequency) to @var{lf} (low frequency) using a symetric moving average smoother with @math{2K+1} points, so that K observations at the beginning and at the end of the  sample are lost in the computation of the filter.
+Implementation of the Baxter and King (1999) band pass filter for @dseries objects. This filter isolates business cycle fluctuations with a period of length ranging between @var{hf} (high frequency) to @var{lf} (low frequency) using a symetric moving average smoother with @math{2K+1} points, so that K observations at the beginning and at the end of the  sample are lost in the computation of the filter.
 @examplehead
 @example
@@ -9226,7 +9323,7 @@ Sanity check of @dseries object @var{A}. Returns @math{1} if there is an error,
 @deftypefn {dseries} {@var{B} = } cumsum (@var{A}[, @var{d}[, @var{v}]])
-Overloads the Matlab/Octave @code{cumsum} function for @dseries objects. The cumulated sum cannot be computed if the variables in @dseries object @var{A} have @code{NaN}s. If a @dates object @var{d} is provided as a second argument, then the method computes the cumulated sum with the additional constraint that the variables in the @dseries object @var{B} are zero in period @var{d}. If a single observation @dseries object @var{v} is provided as a third argument, the cumulated sum in @var{B} is such that @code{B(d)} matches @var{v}.
+Overloads the Matlab/Octave @code{cumsum} function for @dseries objects. The cumulated sum cannot be computed if the variables in @dseries object @var{A} has @code{NaN}s. If a @dates object @var{d} is provided as a second argument, then the method computes the cumulated sum with the additional constraint that the variables in the @dseries object @var{B} are zero in period @var{d}. If a single observation @dseries object @var{v} is provided as a third argument, the cumulated sum in @var{B} is such that @code{B(@var{d})} matches @var{v} (@dseries objects @var{A} and @var{v} must have the same number of variables).
 @examplehead
 @example
@@ -9472,7 +9569,7 @@ The previous code should produce something like:
 @deftypefn {dseries} {@var{C} = } insert (@var{A}, @var{B}, @var{I})
-Inserts variables contained in @dseries object @var{B} in @dseries object @var{A} at positions specified by integer scalars in vector @var{I}, returns augmented @dseries object @var{C}. The integer scalars in @var{I} must take values between @code{1} and @code{A.length()+1} and refers to @var{A}'s column numbers. The @dseries objects @var{A} and @var{B} need not to be defined over the same time ranges, but it is assumled that they have common frequency.
+Inserts variables contained in @dseries object @var{B} in @dseries object @var{A} at positions specified by integer scalars in vector @var{I}, returns augmented @dseries object @var{C}. The integer scalars in @var{I} must take values between @code{1} and @code{A.length()+1} and refers to @var{A}'s column numbers. The @dseries objects @var{A} and @var{B} need not to be defined over the same time ranges, but it is assumed that they have common frequency.
 @examplehead
 @example
@@ -9620,6 +9717,7 @@ ts2 is a dseries object:
 @noindent @remarkhead
 @noindent The overloading of the parenthesis for @dseries objects, allows to easily create new @dseries objects by copying/pasting equations declared in the @code{model} block. For instance, if an Euler equation is defined in the @code{model} block:
 @example
 model;
    ...
@@ -9627,11 +9725,14 @@ model;
    ...
 end;
 @end example
 @noindent and if variables @var{C}, @var{A} and @var{K} are defined as @dseries objects, then by writting:
 @example
 Residuals = 1/C - beta/C(1)*(exp(A(1))*K^(alpha-1)+1-delta) ;
 @end example
-@noindent outside of the @code{model} block, we create a new @dseries object, called @var{Residuals}, for the residuals of the Euler equation (the conditional expectation of the equation defined in the @code{model} block is zero, but the residuals are non zero).
+@noindent outside of the @code{model} block, we create a new @dseries object, called @code{Residuals}, for the residuals of the Euler equation (the conditional expectation of the equation defined in the @code{model} block is zero, but the residuals are non zero).
 @sp 1
@@ -9746,6 +9847,36 @@ ans is a dseries object:
 @sp 1
+@deftypefn{dseries} {@var{C} =} mpower (@var{A}, @var{B})
+Overloads the @code{mpower} (@code{^}) operator for @dseries objects and computes element-by-element power. @var{A} is a @dseries object with @code{N} variables and @code{T} observations. If @var{B} is a real scalar, then @code{mpower(@var{A},@var{B})} returns a @dseries object @var{C} with @code{C.data(t,n)=A.data(t,n)^C}. If @var{B} is a @dseries object with @code{N} variables and @code{T} observations then @code{mpower(@var{A},@var{B})} returns a @dseries object @var{C} with @code{C.data(t,n)=A.data(t,n)^C.data(t,n)}.
+@examplehead
+@example
+>> ts0 = dseries(transpose(1:3));
+>> ts1 = ts0^2
+ts1 is a dseries object:
+   | power(Variable_1,2)
+1Y | 1
+2Y | 4
+3Y | 9
+>> ts2 = ts0^ts0
+ts2 is a dseries object:
+   | power(Variable_1,Variable_1)
+1Y | 1
+2Y | 4
+3Y | 27
+@end example
+@end deftypefn
+@sp 1
 @deftypefn{dseries} {@var{C} =} mrdivide (@var{A}, @var{B})
 Overloads the @code{mrdivide} (@code{/}) operator for @dseries objects, element by element division (like the @code{./} Matlab/Octave operator). If both @var{A} and @var{B} are @dseries objects, they do not need to be defined over the same time ranges. If @var{A} and @var{B} are @dseries object with @math{T_A} and @math{T_B} observations and @math{N_A} and @math{N_B} variables, then  @math{N_A} must be equal to @math{N_B} or @math{1} and  @math{N_B} must be equal to @math{N_A} or @math{1}. If @math{T_A=T_B}, @code{isequal(A.init,B.init)} returns 1 and @math{N_A=N_B}, then the @code{mrdivide} operator will compute for each couple  @math{(t,n)}, with @math{1<=t<=T_A} and @math{1<=n<=N_A}, @code{C.data(t,n)=A.data(t,n)/B.data(t,n)}. If @math{N_B} is equal to @math{1} and @math{N_A>1}, the smaller @dseries object (@var{B}) is ``broadcast'' across the larger @dseries (@var{A}) so that they have compatible shapes, @code{mrdivides} operator will divide each variable defined in @var{A} by the variable in @var{B}, observation per observation. If @var{B} is a double scalar, then the method @code{mrdivide} will divide all the observations/variables in @var{A} by @var{B}.
@@ -9865,9 +9996,9 @@ Overloads the @code{plus} (@code{+}) operator for @dseries objects, element by e
 @sp 1
-@deftypefn{dseries} {@var{B} =} pop (@var{A}[, @var{a}])
+@deftypefn{dseries} {@var{C} =} pop (@var{A}[, @var{B}])
-Removes variable @var{a} from @dseries object @var{A}. By default, if the second argument is not provided, the last variable is removed.
+Removes variable @var{B} from @dseries object @var{A}. By default, if the second argument is not provided, the last variable is removed.
 @examplehead
 @example
@@ -9942,26 +10073,32 @@ ts1 is a dseries object:
 @sp 1
-@deftypefn{dseries} save (@var{A}[, @var{basename}[, @var{format}]])
+@deftypefn{dseries} save (@var{A}, @var{basename}[, @var{format}])
-Overloads the Matlab/Octave @code{save} function, saves @dseries object @var{A} to disk. Possible formats are @code{csv} (this is the default), @code{m} (Matlab/Octave script), and @code{mat} (Matlab binary data file). The name of the file without extension is specified by @var{basename}, by default @var{basename} is the name of the first input (namely, the @dseries object @var{A}).
+Overloads the Matlab/Octave @code{save} function, saves @dseries object @var{A} to disk. Possible formats are @code{csv} (this is the default), @code{m} (Matlab/Octave script), and @code{mat} (Matlab binary data file). The name of the file without extension is specified by @var{basename}.
 @examplehead
 @example
 >> ts0 = dseries(ones(2,2));
->> ts0.save();
+>> ts0.save('ts0');
 @end example
 @noindent The last command will create a file @code{ts0.csv} with the following content:
 @example
 ,Variable_1,Variable_2
 1Y,               1,               1
 2Y,               1,               1
 @end example
-To create a Matlab/octave script, the following command:
+@noindent To create a Matlab/octave script, the following command:
 @example
->> ts0.save([],'m');
+>> ts0.save('ts0','m');
 @end example
-will produce a file @code{ts0.m} with the following content:
+@noindent will produce a file @code{ts0.m} with the following content:
 @example
 % File created on 14-Nov-2013 12:08:52.
@@ -9979,6 +10116,7 @@ Variable_2 = [
              1
              1];
 @end example
 @noindent The generated (@code{csv}, @code{m}, or @code{mat}) files can be loaded when instantiating a @dseries object as explained above.
 @end deftypefn
@@ -10206,7 +10344,7 @@ command. Default: @code{`!'}
 @end table
 @end defmethod
-@defmethod Report addGraph data, figname, graphSize, showGrid, showLegend, showLegendBox, legendLocation, legendOrientation, legendFontSize, seriesToUse, shade, shadeColor, shadeOpacity, title, xlabel, ylabel, xrange, xTickLabels, yrange, showZeroline
+@defmethod Report addGraph data, figname, figDirName, graphSize, showGrid, showLegend, showLegendBox, legendLocation, legendOrientation, legendFontSize, seriesToUse, shade, shadeColor, shadeOpacity, title, xlabel, ylabel, xrange, xTicks, xTickLabels, yrange, showZeroline
 Adds a @code{Graph} to a @code{Section}.
 @optionshead
 @table @code
@@ -10219,6 +10357,10 @@ The @code{dseries} that provides the data for the graph. Default:
 The name to use when saving this figure. Default: @code{[tempname
 `.tex']}
+@item figDirName, @code{STRING}
+The name of the folder in which to store this figure. Default:
+@code{tmpFigDir}
 @item graphSize, @code{NUMERICAL_VECTOR}
 The width and height to be passed to the third and fourth elements of
 the array passed to the @code{`Position'} option of Matlab's
@@ -10275,9 +10417,16 @@ The y-axis label. Default: @code{none}
 @item xrange, @code{dates}
 The boundary on the x-axis to display in the graph. Default: all
+@anchor{xTicks}
+@item xTicks, @code{NUMERICAL_VECTOR}
+Used only in conjunction with @ref{xTickLabels}, this option denotes
+the numerical position of the label along the x-axis. The positions
+begin at @math{1}. Default: set by Matlab/Octave.
+@anchor{xTickLabels}
 @item xTickLabels, @code{CELL_ARRAY_STRINGS}
-The labels to use for the xticks in the graph. Default: the dates of
+The labels to be mapped to the ticks provided by
-the @code{dseries}
+@ref{xTicks}. Default: the dates of the @code{dseries}
 @item yrange, @code{NUMERICAL_VECTOR}
 The boundary on the y-axis to display in the graph, represented as a
@@ -10515,8 +10664,12 @@ Two examples of a small RBC model in a stochastic setup, presented in
 @cite{Collard (2001)} (see the file @file{guide.pdf} which comes with
 Dynare).
+@item example3.mod
+A small RBC model in a stochastic setup, presented in
+@cite{Collard (2001)}. The steady state is solved analytically using the  @code{steady_state_model} block (@pxref{steady_state_model}).
 @item fs2000.mod
-A cash in advance model, estimated by @cite{Schorfheide (2000)}.
+A cash in advance model, estimated by @cite{Schorfheide (2000)}. The file shows how to use Dynare for estimation.
 @item fs2000_nonstationary.mod
 The same model than @file{fs2000.mod}, but written in non-stationary
@@ -10524,12 +10677,15 @@ form. Detrending of the equations is done by Dynare.
 @item bkk.mod
 Multi-country RBC model with time to build, presented in @cite{Backus,
-Kehoe and Kydland (1992)}.
+Kehoe and Kydland (1992)}. The file shows how to use Dynare's macro-processor.
 @item agtrend.mod
 Small open economy RBC model with shocks to the growth trend, presented
 in @cite{Aguiar and Gopinath (2004)}.
+@item NK_baseline.mod
+Baseline New Keynesian Model estimated in @cite{Fernández-Villaverde (2010)}. It demonstrates how to use an explicit steady state file to update parameters and call a numerical solver.
 @end table
 @node Dynare misc commands
@@ -10627,7 +10783,7 @@ Aguiar, Mark and Gopinath, Gita (2004): ``Emerging Market Business
 Cycles: The Cycle is the Trend,'' @i{NBER Working Paper}, 10734
 @item
-Andreasen, Martin M., Fernández-Villaverde, Jesús and Juan Rubio-Ramírez (2013): ``The Pruned State-Space System for Non-Linear DSGE Models: Theory and Empirical Applications,'' @i{NBER Working Paper}, 18983
+Andreasen, Martin M., Jesús Fernández-Villaverde, and Juan Rubio-Ramírez (2013): ``The Pruned State-Space System for Non-Linear DSGE Models: Theory and Empirical Applications,'' @i{NBER Working Paper}, 18983
 @item
 Backus, David K., Patrick J. Kehoe, and Finn E. Kydland (1992):
@@ -10645,8 +10801,7 @@ monitoring  convergence   of  iterative  simulations,''   @i{Journal  of
 computational and graphical statistics}, 7, pp. 434--455
 @item
-Cardoso, Margarida F., R. L. Salcedo and S. Feyo de Azevedo (1996): ``The simplex simulated annealing approach to continuous non-linear optimization'', @i{Computers chem. Engng}, 20(9), 1065-1080
+Cardoso, Margarida F., R. L. Salcedo and S. Feyo de Azevedo (1996): ``The simplex simulated annealing approach to continuous non-linear optimization,'' @i{Computers chem. Engng}, 20(9), 1065-1080
 @item
 Collard, Fabrice (2001): ``Stochastic simulations with Dynare: A practical guide''
@@ -10696,9 +10851,13 @@ Fernández-Villaverde, Jesús and Juan Rubio-Ramírez (2005): ``Estimating
 Dynamic Equilibrium Economies: Linear versus Nonlinear Likelihood,''
 @i{Journal of Applied Econometrics}, 20, 891--910
+@item
+Fernández-Villaverde, Jesús (2010): ``The econometrics of DSGE models,''
+@i{SERIEs}, 1, 3--49
 @item
 Geweke, John (1992): ``Evaluating the accuracy of sampling-based approaches
-to the calculation of posterior moments'', in J.O. Berger, J.M. Bernardo, 
+to the calculation of posterior moments,'' in J.O. Berger, J.M. Bernardo,
 A.P. Dawid, and A.F.M. Smith (eds.) Proceedings of the Fourth Valencia
 International Meeting on Bayesian Statistics, pp. 169--194, Oxford University Press

--- a/examples/NK_baseline.mod
+++ b/examples/NK_baseline.mod
@@ -15,7 +15,14 @@
 * equations. Moreover, it makes use of a steady state file to i) set 
 * parameters that depend on other parameters that are potentially estimated
 * and ii) solve a nonlinear equation using a numerical solver to find the steady
- * state of labor.
+ * state of labor. It provides an example on how the steady state file can be used
+ * to circumvent some of the limitation of Dynare mod-file by accessing an external
+ * file that allows calling general Matlab routines. These capacities will mostly be 
+ * interesting for power users. If one just wants to provide analytical steady state 
+ * values and update parameters, the steady_state_model-block allows an easy and convenient
+ * alternative. It even allows calling numerical solvers like fsolve. For an example, see
+ * example3.mod
+ * 
 * The model is written in the beginning of period stock notation. To make the model
 * conform with Dynare's end of period stock notation, we use the 
 * predetermined_variables-command.

--- a/examples/NK_baseline_steadystate.m
+++ b/examples/NK_baseline_steadystate.m
-function [ys,check] = NK_baseline_steadystate(ys,exe)
+function [ys,check] = NK_baseline_steadystate(ys,exo)
-global M_ lgy_
+% function [ys,check] = NK_baseline_steadystate(ys,exo)
+% computes the steady state for the NK_baseline.mod and uses a numerical
-if isfield(M_,'param_nbr') == 1
+% solver to do so
+% Inputs: 
+%   - ys        [vector] vector of initial values for the steady state of
+%                   the endogenous variables
+%   - exo       [vector] vector of values for the exogenous variables
+%
+% Output: 
+%   - ys        [vector] vector of steady state values fpr the the endogenous variables
+%   - check     [scalar] set to 0 if steady state computation worked and to
+%                    1 of not (allows to impos restriction on parameters)
+global M_ 
+% read out parameters to access them with their name
 NumberOfParameters = M_.param_nbr;
-for i = 1:NumberOfParameters
+for ii = 1:NumberOfParameters
-  paramname = deblank(M_.param_names(i,:));
+  paramname = deblank(M_.param_names(ii,:));
-  eval([ paramname ' = M_.params(' int2str(i) ');']);
+  eval([ paramname ' = M_.params(' int2str(ii) ');']);
 end
+% initialize indicator
 check = 0;
-end
 %% Enter model equations here
@@ -32,6 +45,11 @@ Lambdax=mu_z;
 %set the parameter gammma1
 gammma1=mu_z*mu_I/betta-(1-delta);
+if gammma1<0 % parameter violates restriction; Preventing this cannot be implemented via prior restriction as it is a composite of different parameters and the valid prior region has unknown form
+    check=1; %set failure indicator
+    return; %return without updating steady states
+end
 r=1*gammma1;
 R=1+(PI*mu_z/betta-1);
@@ -49,9 +67,17 @@ vp=(1-thetap)/(1-thetap*PI^((1-chi)*epsilon))*PIstar^(-epsilon);
 vw=(1-thetaw)/(1-thetaw*PI^((1-chiw)*eta)*mu_z^eta)*PIstarw^(-eta);
 tempvaromega=alppha/(1-alppha)*w/r*mu_z*mu_I;
-ld=fsolve(@(ld)(1-betta*thetaw*mu_z^(eta-1)*PI^(-(1-chiw)*(1-eta)))/(1-betta*thetaw*mu_z^(eta*(1+gammma))*PI^(eta*(1-chiw)*(1+gammma)))...
+[ld,fval,exitflag]=fsolve(@(ld)(1-betta*thetaw*mu_z^(eta-1)*PI^(-(1-chiw)*(1-eta)))/(1-betta*thetaw*mu_z^(eta*(1+gammma))*PI^(eta*(1-chiw)*(1+gammma)))...
 -(eta-1)/eta*wstar/(varpsi*PIstarw^(-eta*gammma)*ld^gammma)*((1-h*mu_z^(-1))^(-1)-betta*h*(mu_z-h)^(-1))*...
 ((mu_A*mu_z^(-1)*vp^(-1)*tempvaromega^alppha-tempvaromega*(1-(1-delta)*(mu_z*mu_I)^(-1)))*ld-vp^(-1)*Phi)^(-1),0.25,options);
+if exitflag <1
+    %indicate the SS computation was not sucessful; this would also be detected by Dynare
+    %setting the indicator here shows how to use this functionality to
+    %filter out parameter draws
+    check=1; %set failure indicator
+    return; %return without updating steady states
+end
 l=vw*ld;
 k=tempvaromega*ld;
@@ -68,27 +94,12 @@ g2=epsilon/(epsilon-1)*g1;
 %% end own model equations
+for iter = 1:length(M_.params) %update parameters set in the file
-for iter = 1:length(M_.params)
  eval([ 'M_.params(' num2str(iter) ') = ' M_.param_names(iter,:) ';' ])
 end
-if isfield(M_,'param_nbr') == 1
+NumberOfEndogenousVariables = M_.orig_endo_nbr; %auxiliary variables are set automatically
+for ii = 1:NumberOfEndogenousVariables
-if isfield(M_,'orig_endo_nbr') == 1
+  varname = deblank(M_.endo_names(ii,:));
-NumberOfEndogenousVariables = M_.orig_endo_nbr;
+  eval(['ys(' int2str(ii) ') = ' varname ';']);
-else
-NumberOfEndogenousVariables = M_.endo_nbr;
-end
-ys = zeros(NumberOfEndogenousVariables,1);
-for i = 1:NumberOfEndogenousVariables
-  varname = deblank(M_.endo_names(i,:));
-  eval(['ys(' int2str(i) ') = ' varname ';']);
-end
-else
-ys=zeros(length(lgy_),1);
-for i = 1:length(lgy_)
-    ys(i) = eval(lgy_(i,:));
-end
-check = 0;
 end
--- a/examples/example3.mod
+++ b/examples/example3.mod
+/*
+ * Example 1 from F. Collard (2001): "Stochastic simulations with DYNARE:
+ * A practical guide" (see "guide.pdf" in the documentation directory).
+ * 
+ * This file uses the steady_state_model-block to provide analytical steady state values.
+ * To do so, the equations of the model have been transformed into a non-linear equation in 
+ * labor h. Within the steady_state_model-block, a helper function is called that uses fsolve
+ * to solve this non-linear equation. The use of the helper function is necessary to avoid 
+ * interference of the Matlab syntax with Dynare's preprocessor. A more complicated alternative 
+ * that provides more flexibility in the type of commands executed and functions called is the use 
+ * of an explicit steady state file. See the NK_baseline.mod in the Examples Folder.
+ * 
+ * This mod-file also shows how to use Dynare's capacities to generate TeX-files of the model equations. 
+ * If you want to see the model equations belonging to this mod-file, run it using Dynare 
+ * and then use a TeX-editor to compile the TeX-files generated.
+ */
+/*
+ * Copyright (C) 2013 Dynare Team
+ *
+ * This file is part of Dynare.
+ *
+ * Dynare is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * Dynare is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Dynare.  If not, see <http://www.gnu.org/licenses/>.
+ */
+var y, c, k, a, h, b;
+varexo e, u;
+parameters beta $\beta$
+     rho $\rho$
+     alpha $\alpha$
+     delta $\delta$
+     theta $\theta$
+     psi $\psi$
+     tau $\tau$;
+alpha = 0.36;
+rho   = 0.95;
+tau   = 0.025;
+beta  = 0.99;
+delta = 0.025;
+psi   = 0;
+theta = 2.95;
+phi   = 0.1;
+model;
+c*theta*h^(1+psi)=(1-alpha)*y;
+k = beta*(((exp(b)*c)/(exp(b(+1))*c(+1)))
+    *(exp(b(+1))*alpha*y(+1)+(1-delta)*k));
+y = exp(a)*(k(-1)^alpha)*(h^(1-alpha));
+k = exp(b)*(y-c)+(1-delta)*k(-1);
+a = rho*a(-1)+tau*b(-1) + e;
+b = tau*a(-1)+rho*b(-1) + u;
+end;
+steady_state_model;
+h=example3_steady_state_helper(alpha,beta,delta,psi,theta);
+k=((1/beta-(1-delta))/alpha)^(1/(alpha-1))*h;
+y = k^alpha*h^(1-alpha);
+c=(1-alpha)*y/(theta*h^(1+psi));
+a=0;
+b=0;
+end;
+shocks;
+var e; stderr 0.009;
+var u; stderr 0.009;
+var e, u = phi*0.009*0.009;
+end;
+//use command to generate TeX-Files with dynamic and static model equations
+write_latex_dynamic_model;
+write_latex_static_model;
+stoch_simul;
--- a/examples/example3_steady_state_helper.m
+++ b/examples/example3_steady_state_helper.m
+function h=example3_steady_state_helper(alpha,beta,delta,psi,theta)
+options=optimset('Display','Final','TolX',1e-10,'TolFun',1e-10);
+h=fsolve(@(h)1- ((((((1/beta-(1-delta))/alpha)^(1/(alpha-1))*h)^(alpha-1))*(h^(1-alpha))-(((1-alpha)*((((1/beta-(1-delta))/alpha)^(1/(alpha-1)))^alpha))/(theta*h^psi))/(((1/beta-(1-delta))/alpha)^(1/(alpha-1))*h))+(1-delta)),0.2,options);
--- a/examples/fs2000.mod
+++ b/examples/fs2000.mod
@@ -87,6 +87,32 @@ var e_a; stderr 0.014;
 var e_m; stderr 0.005;
 end;
+steady_state_model;
+  dA = exp(gam);
+  gst = 1/dA;
+  m = mst;
+  khst = ( (1-gst*bet*(1-del)) / (alp*gst^alp*bet) )^(1/(alp-1));
+  xist = ( ((khst*gst)^alp - (1-gst*(1-del))*khst)/mst )^(-1);
+  nust = psi*mst^2/( (1-alp)*(1-psi)*bet*gst^alp*khst^alp );
+  n  = xist/(nust+xist);
+  P  = xist + nust;
+  k  = khst*n;
+  l  = psi*mst*n/( (1-psi)*(1-n) );
+  c  = mst/P;
+  d  = l - mst + 1;
+  y  = k^alp*n^(1-alp)*gst^alp;
+  R  = mst/bet;
+  W  = l/n;
+  ist  = y-c;
+  q  = 1 - d;
+  e = 1;
+  gp_obs = m/dA;
+  gy_obs = dA;
+end;
 steady;
 check;

--- a/matlab/@dseries/disp.m
+++ b/matlab/@dseries/disp.m
@@ -23,7 +23,7 @@ separator = repmat(' | ',A.nobs+1,1);
 vspace = ' ';
 TABLE = ' ';
 for t=1:A.nobs
-    TABLE = char(TABLE, format(A.dates(t)));
+    TABLE = char(TABLE, date2string(A.dates(t)));
 end
 for i = 1:A.vobs
    TABLE = horzcat(TABLE,separator);

--- a/matlab/@dseries/mpower.m
+++ b/matlab/@dseries/mpower.m
+function A = mpower(B,C) % --*-- Unitary tests --*--
+%@info:
+%! @deftypefn {Function File} {@var{A} =} mpower (@var{B},@var{C})
+%! @anchor{@dseries/mpower}
+%! @sp 1
+%! Overloads the mpower method for the Dynare time series class (@ref{dseries}).
+%! @sp 2
+%! @strong{Inputs}
+%! @sp 1
+%! @table @ @var
+%! @item B
+%! Dynare time series object instantiated by @ref{dseries}, with T observations and N variables.
+%! @item C
+%! Real scalar or a dseries object with T observations and N variables.
+%! @end table
+%! @sp 1
+%! @strong{Outputs}
+%! @sp 1
+%! @table @ @var
+%! @item A
+%! dseries object with T observations and N variables.
+%! @end deftypefn
+%@eod:
+% Copyright (C) 2013 Dynare Team
+%
+% This file is part of Dynare.
+%
+% Dynare is free software: you can redistribute it and/or modify
+% it under the terms of the GNU General Public License as published by
+% the Free Software Foundation, either version 3 of the License, or
+% (at your option) any later version.
+%
+% Dynare is distributed in the hope that it will be useful,
+% but WITHOUT ANY WARRANTY; without even the implied warranty of
+% MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+% GNU General Public License for more details.
+%
+% You should have received a copy of the GNU General Public License
+% along with Dynare.  If not, see <http://www.gnu.org/licenses/>.
+if isdseries(B) && isnumeric(C) && isreal(C) && isscalar(C)
+    A = dseries();
+    A.freq = B.freq;
+    A.init = B.init;
+    A.dates = B.dates;
+    A.nobs = B.nobs;
+    A.vobs = B.vobs;
+    A.name = cell(A.vobs,1);
+    A.tex = cell(A.vobs,1);
+    for i=1:A.vobs
+        A.name(i) = {['power(' B.name{i} ',' num2str(C) ')']};
+        A.tex(i) = {[B.tex{i} '^' num2str(C) ]};
+    end
+    A.data = B.data.^C;
+    return
+end
+if isdseries(B) && isdseries(C)
+    if isequal(B.nobs,C.nobs) && isequal(B.vobs,C.vobs) && isequal(B.freq,C.freq)
+        A = dseries();
+        A.freq = B.freq;
+        A.init = B.init;
+        A.dates = B.dates;
+        A.nobs = B.nobs;
+        A.vobs = B.vobs;
+        A.name = cell(A.vobs,1);
+        A.tex = cell(A.vobs,1);
+        for i=1:A.vobs
+            A.name(i) = {['power(' B.name{i} ',' C.name{i} ')']};
+            A.tex(i) = {[B.tex{i} '^{' C.tex{i} '}']};
+        end
+        A.data = B.data.^C.data;
+    else
+        error('dseries::mpower: If both input arguments are dseries objects, they must have the same numbers of variables and observations and common frequency!')
+    end
+    return
+end
+error(['dseries::mpower: Wrong calling sequence!'])
+%@test:1
+%$ % Define a datasets.
+%$ A = rand(10,2); B = randn(10,2);
+%$
+%$ % Define names
+%$ A_name = {'A1';'A2'}; B_name = {'B1';'B2'};
+%$
+%$
+%$ % Instantiate a time series object.
+%$ try
+%$    ts1 = dseries(A,[],A_name,[]);
+%$    ts2 = dseries(B,[],B_name,[]);
+%$    ts3 = ts1^ts2;
+%$    t = 1;
+%$ catch
+%$    t = 0;
+%$ end
+%$
+%$ if t(1)
+%$    t(2) = dyn_assert(ts3.vobs,2);
+%$    t(3) = dyn_assert(ts3.nobs,10);
+%$    t(4) = dyn_assert(ts3.data,A.^B,1e-15);
+%$    t(5) = dyn_assert(ts3.name,{'power(A1,B1)';'power(A2,B2)'});
+%$    t(6) = dyn_assert(ts3.tex,{'A1^{B1}';'A2^{B2}'});
+%$ end
+%$ T = all(t);
+%@eof:1
+%@test:2
+%$ % Define a datasets.
+%$ A = rand(10,2);
+%$
+%$ % Define names
+%$ A_name = {'A1';'A2'};
+%$
+%$
+%$ % Instantiate a time series object.
+%$ try
+%$    ts1 = dseries(A,[],A_name,[]);
+%$    ts3 = ts1^2;
+%$    t = 1;
+%$ catch
+%$    t = 0;
+%$ end
+%$
+%$ if t(1)
+%$    t(2) = dyn_assert(ts3.vobs,2);
+%$    t(3) = dyn_assert(ts3.nobs,10);
+%$    t(4) = dyn_assert(ts3.data,A.^2,1e-15);
+%$    t(5) = dyn_assert(ts3.name,{'power(A1,2)';'power(A2,2)'});
+%$    t(6) = dyn_assert(ts3.tex,{'A1^2';'A2^2'});
+%$ end
+%$ T = all(t);
+%@eof:2
\ No newline at end of file
--- a/matlab/@dseries/plot.m
+++ b/matlab/@dseries/plot.m
@@ -56,6 +56,7 @@ switch ndseries
        end
        hh = plot(ts.data);
    end
+    axis tight;
    id = get(gca,'XTick');
    if isequal(id(1),0)
        dates = strings([ts.dates(1)-1,ts.dates(id(2:end))]);

--- a/matlab/CheckPath.m
+++ b/matlab/CheckPath.m
-function DirectoryName = CheckPath(type,dname)
+function [DirectoryName, info] = CheckPath(type,dname)
 % Creates the subfolder "./M_.dname/type" if it does not exist yet.
 %
 % INPUTS
@@ -6,12 +6,13 @@ function DirectoryName = CheckPath(type,dname)
 %    dname  [string]    Name of the directory
 %
 % OUTPUTS
-%    none.
+%    DirectoryName      string, name of the directory (with path).
+%    info               integer scalar, equal to 1 if the routine creates directory dname/type, zero otherwise.
 %
 % SPECIAL REQUIREMENTS
 %    none
-% Copyright (C) 2005-2012 Dynare Team
+% Copyright (C) 2005-2013 Dynare Team
 %
 % This file is part of Dynare.
 %
@@ -28,6 +29,8 @@ function DirectoryName = CheckPath(type,dname)
 % You should have received a copy of the GNU General Public License
 % along with Dynare.  If not, see <http://www.gnu.org/licenses/>.
+info = 0;
 DirectoryName = [ dname '/' type ];
 if ~isdir(dname)
@@ -44,4 +47,5 @@ if ~isdir(DirectoryName)
        delete(DirectoryName)
    end
    mkdir('.',DirectoryName);
+    info = 1;
 end
--- a/matlab/check.m
+++ b/matlab/check.m
@@ -107,7 +107,7 @@ if options.noprint == 0
    if result
        disp('The rank condition is verified.')
    else
-        disp('The rank conditions ISN''T verified!')
+        disp('The rank condition ISN''T verified!')
    end
    skipline()
 end
--- a/matlab/check_posterior_analysis_data.m
+++ b/matlab/check_posterior_analysis_data.m
@@ -22,16 +22,19 @@ if nargout>1
    description = '';
 end
-%% Get informations about mcmc files. 
+[MetropolisFolder, info] = CheckPath('metropolis',M_.dname);
-if ~exist([ M_.dname '/metropolis'],'dir')
+% Get informations about mcmc files.
+if info
    disp('check_posterior_analysis_data:: Can''t find any mcmc file!')
    return
 end
 mhname = get_name_of_the_last_mh_file(M_);
-mhdate = get_date_of_a_file(mhname);
+mhdate = get_date_of_a_file([MetropolisFolder filesep mhname]);
-%% Get informations about _posterior_draws files.
+% Get informations about _posterior_draws files.
-drawsinfo = dir([ M_.dname '/metropolis/' M_.fname '_posterior_draws*.mat']);
+drawsinfo = dir([ MetropolisFolder filesep M_.fname '_posterior_draws*.mat']);
 if isempty(drawsinfo)
    info = 1; % select_posterior_draws has to be called first.
    if nargout>1
@@ -40,8 +43,7 @@ if isempty(drawsinfo)
    return
 else
    number_of_last_posterior_draws_file = length(drawsinfo);
-    pddate = get_date_of_a_file([ M_.dname '/metropolis/' M_.fname '_posterior_draws'...
+    pddate = get_date_of_a_file([ MetropolisFolder filesep M_.fname '_posterior_draws' int2str(number_of_last_posterior_draws_file) '.mat']);
-                        int2str(number_of_last_posterior_draws_file) '.mat']);
    if pddate<mhdate
        info = 2; % _posterior_draws files have to be updated.
        if nargout>1
@@ -56,7 +58,7 @@ else
    end
 end
-%% Get informations about posterior data files.
+% Get informations about posterior data files.
 switch type
  case 'variance'
    generic_post_data_file_name = 'Posterior2ndOrderMoments';
@@ -69,7 +71,7 @@ switch type
  otherwise
    disp('This feature is not yest implemented!')
 end
-pdfinfo = dir([ M_.dname '/metropolis/' M_.fname '_' generic_post_data_file_name '*']);
+pdfinfo = dir([ MetropolisFolder filesep M_.fname '_' generic_post_data_file_name '*']);
 if isempty(pdfinfo)
    info = 4; % posterior draws have to be processed.
    if nargout>1
@@ -79,8 +81,7 @@ if isempty(pdfinfo)
 else
    number_of_the_last_post_data_file = length(pdfinfo);
    name_of_the_last_post_data_file = ...
-        [ pwd filesep M_.dname ...
+        [ pwd filesep MetropolisFolder filesep ...
-          filesep 'metropolis' filesep ...
          M_.fname '_' ... 
          generic_post_data_file_name ...
          int2str(number_of_the_last_post_data_file) ...

--- a/matlab/dynare_estimation_init.m
+++ b/matlab/dynare_estimation_init.m
@@ -130,13 +130,18 @@ if ~isempty(estim_params_) && ~isempty(options_.mode_file) && ~options_.mh_poste
    number_of_estimated_parameters = length(xparam1);
    mode_file = load(options_.mode_file);
    if number_of_estimated_parameters>length(mode_file.xparam1)
+        % More estimated parameters than parameters in the mode file.
        skipline()
        disp(['The posterior mode file ' options_.mode_file ' has been generated using another specification of the model or another model!'])
        disp(['Your mode file contains estimates for ' int2str(length(mode_file.xparam1)) ' parameters, while you are attempting to estimate ' int2str(number_of_estimated_parameters) ' parameters:'])
+        md = []; xd = [];
        for i=1:number_of_estimated_parameters
            id = strmatch(deblank(bayestopt_.name(i,:)),mode_file.parameter_names,'exact');
            if isempty(id)
-                disp(['--> Estimated parameter ' bayestopt_.name{i} ' is not present in the loaded mod_file.'])
+                disp(['--> Estimated parameter ' bayestopt_.name{i} ' is not present in the loaded mode file (prior mean will be used, if possible).'])
+            else
+                xd = [xd; i];
+                md = [md; id];
            end
        end
        for i=1:length(mode_file.xparam1)
@@ -145,20 +150,30 @@ if ~isempty(estim_params_) && ~isempty(options_.mode_file) && ~options_.mh_poste
                disp(['--> Parameter ' mode_file.parameter_names{i} ' is not estimated according to the current mod file.'])
            end
        end
-        error('Please change the mode_file option or the list of estimated parameters.')
+        if ~options_.mode_compute
+            % The posterior mode is not estimated.
+            error('Please change the mode_file option, the list of estimated parameters or set mode_compute>0.')
+        else
+            % The posterior mode is estimated, the Hessian evaluated at the mode is not needed so we set values for the parameters missing in the mode file using the prior mean. 
+            if ~isempty(xd)
+                xparam1(xd) = mode_file.xparam1(md);
+            else
+                error('Please remove the mode_file option.')
+            end
+        end
    elseif number_of_estimated_parameters<length(mode_file.xparam1)
+        % Less estimated parameters than parameters in the mode file.
        skipline()
        disp(['The posterior mode file ' options_.mode_file ' has been generated using another specification of the model or another model!'])
        disp(['Your mode file contains estimates for ' int2str(length(mode_file.xparam1)) ' parameters, while you are attempting to estimate only ' int2str(number_of_estimated_parameters) ' parameters:'])
-        Id = [];
+        md = []; xd = [];
        for i=1:number_of_estimated_parameters
            id = strmatch(deblank(bayestopt_.name(i,:)),mode_file.parameter_names,'exact');
            if isempty(id)
-                disp(['--> Estimated parameter ' deblank(bayestopt_.name(i,:)) ' is not present in the loaded mode file.'])
+                disp(['--> Estimated parameter ' deblank(bayestopt_.name(i,:)) ' is not present in the loaded mode file (prior mean will be used, if possible).'])
-                Id = [];
-                break
            else
-                Id = [Id; id];
+                xd = [xd; i];
+                md = [md; id];
            end
        end
        for i=1:length(mode_file.xparam1)
@@ -167,59 +182,72 @@ if ~isempty(estim_params_) && ~isempty(options_.mode_file) && ~options_.mh_poste
                disp(['--> Parameter ' mode_file.parameter_names{i} ' is not estimated according to the current mod file.'])
            end
        end
-        if isempty(Id)
+        if ~options_.mode_compute
-            % None of the estimated parameters are present in the mode_file.
+            % The posterior mode is not estimated. If possible, fix the mode_file.
-            error('Please change the mode_file option or the list of estimated parameters.')
+            if isequal(length(xd),number_of_estimated_parameters)
-        else
-            % If possible, fix the mode_file.
-            if isequal(length(Id),number_of_estimated_parameters)
                disp('==> Fix mode file (remove unused parameters).')
-                mode_file.parameter_names = mode_file.parameter_names(Id,:);
+                xparam1 = mode_file.xparam1(md);
-                mode_file.xparam1 = mode_file.xparam1(Id);
                if isfield(mode_file,'hh')
-                    mode_file.hh = mode_file.hh(Id,Id);
+                    hh = mode_file.hh(md,md);
                end
+            else
+                error('Please change the mode_file option, the list of estimated parameters or set mode_compute>0.')
+            end
+        else
+            % The posterior mode is estimated, the Hessian evaluated at the mode is not needed so we set values for the parameters missing in the mode file using the prior mean. 
+            if ~isempty(xd)
+                xparam1(xd) = mode_file.xparam1(md);
+            else
+                % None of the estimated parameters are present in the mode_file.
+                error('Please remove the mode_file option.')
            end
        end
    else
        % The number of declared estimated parameters match the number of parameters in the mode file. 
        % Check that the parameters in the mode file and according to the current mod file are identical.
        if isequal(mode_file.parameter_names, bayestopt_.name)
-            % Ok! Nothing to do here.
+            xparam1 = mode_file.xparam1;
+            if isfield(mode_file,'hh')
+                hh = mode_file.hh;
+            end
        else
            skipline()
            disp(['The posterior mode file ' options_.mode_file ' has been generated using another specification of the model or another model!'])
-            % Check if this only an ordering issue.
+            % Check if this only an ordering issue or if the missing parameters can be initialized with the prior mean.
-            Id = [];
+            md = []; xd = [];
            for i=1:number_of_estimated_parameters
                id = strmatch(deblank(bayestopt_.name(i,:)), mode_file.parameter_names,'exact');
                if isempty(id)
                    disp(['--> Estimated parameter ' bayestopt_.name{i} ' is not present in the loaded mode file.'])
-                    Id = [];
-                    break
                else
-                    Id = [Id; id];
+                    xd = [xd; i];
+                    md = [md; id];
                end
            end
-            if isempty(Id)
+            if ~options_.mode_compute
-                % None of the estimated parameters are present in the mode_file.
+                % The posterior mode is not estimated
-                error('Please change the mode_file option or the list of estimated parameters.')
+                if isequal(length(xd), number_of_estimated_parameters)
-            else
+                    % This is an ordering issue.
-                % If possible, fix the mode_file.
+                    xparam1 = mode_file.xparam1(md);
-                if isequal(length(Id),number_of_estimated_parameters)
-                    disp('==> Fix mode file (reorder the parameters).')
-                    mode_file.parameter_names = mode_file.parameter_names(Id,:);
-                    mode_file.xparam1 = mode_file.xparam1(Id);
                    if isfield(mode_file,'hh')
-                        mode_file.hh = mode_file.hh(Id,Id);
+                        hh = mode_file.hh(md,md);
                    end
+                else
+                    error('Please change the mode_file option, the list of estimated parameters or set mode_compute>0.')
                end
+            else
+                % The posterior mode is estimated, the Hessian evaluated at the mode is not needed so we set values for the parameters missing in the mode file using the prior mean. 
+                if ~isempty(xd)
+                    xparam1(xd) = mode_file.xparam1(md);
+                    if isfield(mode_file,'hh')
+                        hh(xd,xd) = mode_file.hh(md,md);
+                    end
+                else
+                    % None of the estimated parameters are present in the mode_file.
+                    error('Please remove the mode_file option.')
                end
            end
        end
-    xparam1 = mode_file.xparam1;
-    if isfield(mode_file,'hh')
-        hh = mode_file.hh;
    end
    skipline()
 end

--- a/matlab/dynare_identification.m
+++ b/matlab/dynare_identification.m
@@ -207,15 +207,23 @@ else
    name_tex = [cellstr(M_.exo_names_tex); cellstr(M_.param_names_tex)];
 end
+skipline()
+disp(['==== Identification analysis ====' ]),
+skipline()
+if nparam<2,
+    options_ident.advanced=0;
+    advanced = options_ident.advanced;
+    disp('There is only one parameter to study for identitification.')
+    disp('The advanced option is re-set to 0.')
+    skipline()
+end
 options_ident = set_default_option(options_ident,'max_dim_cova_group',min([2,nparam-1]));
 options_ident.max_dim_cova_group = min([options_ident.max_dim_cova_group,nparam-1]);
 MaxNumberOfBytes=options_.MaxNumberOfBytes;
 store_options_ident = options_ident;
-skipline()
-disp(['==== Identification analysis ====' ]),
-skipline()
 if iload <=0,
@@ -326,6 +334,8 @@ if iload <=0,
            disp('----------- ')
            skipline()
            return
+        else
+            parameters = 'Random_prior_params';
        end
    else
    idehess_point.params=params;
@@ -336,6 +346,7 @@ if iload <=0,
 %     normJ = max(abs(siJ)')';
 %     normLRE = max(abs(siLRE)')';
    save([IdentifDirectoryName '/' M_.fname '_identif.mat'], 'idehess_point', 'idemoments_point','idemodel_point', 'idelre_point','store_options_ident')
+    save([IdentifDirectoryName '/' M_.fname '_' parameters '_identif.mat'], 'idehess_point', 'idemoments_point','idemodel_point', 'idelre_point','store_options_ident')
    disp_identification(params, idemodel_point, idemoments_point, name, advanced);
    if ~options_.nograph,
        plot_identification(params,idemoments_point,idehess_point,idemodel_point,idelre_point,advanced,parameters,name,IdentifDirectoryName);

--- a/matlab/dynare_sensitivity.m
+++ b/matlab/dynare_sensitivity.m
@@ -281,10 +281,12 @@ if options_gsa.redform && ~isempty(options_gsa.namendo),% ...
        % check existence of the SS_ANOVA toolbox
        if isempty(options_gsa.threshold_redform) && ...
         ~(exist('gsa_sdp','file')==6 || exist('gsa_sdp','file')==2),
-            disp('Download Mapping routines at:')
+            fprintf('\nThe "SS-ANOVA-R: MATLAB Toolbox for the estimation of Smoothing Spline ANOVA models with Recursive algorithms" is missing.\n')
-            disp('http://eemc.jrc.ec.europa.eu/softwareDYNARE-Dowload.htm')
+            fprintf('To obtain it, go to:\n\n')
-            disp(' ' )
+            fprintf('http://ipsc.jrc.ec.europa.eu/?id=790 \n\n')
-            error('Mapping routines missing!')
+            fprintf('and follow the instructions there.\n')
+            fprintf('After obtaining the files, you need to unpack them and set a Matlab Path to those files.\n')
+            error('SS-ANOVA-R Toolbox missing!')
        end
        redform_map(OutputDirectoryName,options_gsa);
No results found