stepan
/
dynare
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add option for storing contemporaneous correlation

time-shift
Johannes Pfeifer 2015-08-10 21:36:48 +02:00
parent beab158a67
commit 698a44c98a
11 changed files with 84 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
doc/dynare.texi
View File

@ -2189,7 +2189,7 @@ possible types of simulations in stochastic mode:
@itemize
@item
@ref{stoch_simul}, if the @code{periods} options is specified
@ref{stoch_simul}, if the @code{periods} option is specified
@item
@ref{forecast} as the initial point at which the forecasts are computed
@ -2419,7 +2419,7 @@ Moreover, as only states enter the recursive policy functions, all values specif
@itemize
@item
in @ref{stoch_simul}, if the @code{periods} options is specified. Note that this only affects the starting point for the simulation, but not for the impulse response functions.
in @ref{stoch_simul}, if the @code{periods} option is specified. Note that this only affects the starting point for the simulation, but not for the impulse response functions.
@item
in @ref{forecast} as the initial point at which the forecasts are computed
@ -3925,6 +3925,11 @@ Tolerance for the suppression of small terms in the display of decision rules. R
smaller than @code{dr_display_tol} are not displayed.
Default value: @code{1e-6}.
@item contemporaneous_correlation
@anchor{contemporaneous_correlation}
Saves the contemporaneous correlation between the endogenous variables in @code{oo_.contemporaneous_correlation}.
Requires the @code{nocorr}-option not to be set.
@end table
@outputhead
@ -3942,6 +3947,8 @@ If options @code{irf} is different from zero, sets @code{oo_.irfs}
the global workspace (this latter way of accessing the IRFs is
deprecated and will disappear in a future version).
If the option @code{contemporaneous_correlation} is different from 0, sets
{oo_.contemporaneous_correlation}, which is described below.
@customhead{Example 1}
@ -3971,14 +3978,15 @@ response functions on 60 periods for variables @code{y} and @code{k}.
@defvr {MATLAB/Octave variable} oo_.mean
After a run of @code{stoch_simul}, contains the mean of the endogenous
variables. Contains theoretical mean if the @code{periods} option is
not present, and empirical mean otherwise. The variables are arranged
not present, and simulated mean otherwise. The variables are arranged
in declaration order.
@end defvr
@defvr {MATLAB/Octave variable} oo_.var
After a run of @code{stoch_simul}, contains the variance-covariance of
the endogenous variables. Contains theoretical variance if the
@code{periods} option is not present (or an approximation thereof for @code{order=2}), and empirical variance
@code{periods} option is not present (or an approximation thereof for @code{order=2}),
and simulated variance
otherwise. The variables are arranged in declaration order.
@end defvr
@ -3990,7 +3998,7 @@ number of the matrix in the cell array corresponds to the order of
autocorrelation. The option @code{ar} specifies the number of
autocorrelation matrices available. Contains theoretical
autocorrelations if the @code{periods} option is not present (or an approximation thereof for @code{order=2}), and
empirical autocorrelations otherwise. The field is only created if stationary variables are present.
simulated autocorrelations otherwise. The field is only created if stationary variables are present.
The element @code{oo_.autocorr@{i@}(k,l)} is equal to the correlation
between @math{y^k_t} and @math{y^l_{t-i}}, where @math{y^k}
@ -4024,13 +4032,18 @@ If a second order approximation has been requested, contains the
vector of the mean correction terms.
@end table
In case of @code{order=2}, the theoretical second moments are a second order accurate approximation of the true second moments, see @code{conditional_variance_decomposition}.
In case of @code{order=2}, the theoretical second moments are a second order
accurate approximation of the true second moments, see @code{conditional_variance_decomposition}.
@end defvr
@anchor{oo_.variance_decomposition}
@defvr {MATLAB/Octave variable} oo_.variance_decomposition
After a run of @code{stoch_simul} when requesting theoretical moments (@code{periods=0}), contains a matrix with the result of the unconditional variance decomposition (i.e. at horizon infinity). The first dimension corresponds to the endogenous variables (in the order of declaration) and the second dimension corresponds to exogenous variables (in the order of declaration). Numbers are in percent and sum up to 100 across columns.
After a run of @code{stoch_simul} when requesting theoretical moments (@code{periods=0}),
contains a matrix with the result of the unconditional variance decomposition (i.e. at horizon infinity).
The first dimension corresponds to the endogenous variables (in the order of declaration) and
the second dimension corresponds to exogenous variables (in the order of declaration).
Numbers are in percent and sum up to 100 across columns.
@end defvr
@anchor{oo_.conditional_variance_decomposition}
@ -4044,6 +4057,15 @@ the order of declaration), the third dimension corresponds to
exogenous variables (in the order of declaration).
@end defvr
@anchor{oo_.contemporaneous_correlation}
@defvr {MATLAB/Octave variable} oo_.contemporaneous_correlation
After a run of @code{stoch_simul} with the
@code{contemporaneous_correlation} option, contains theoretical contemporaneous correlations if the
@code{periods} option is not present (or an approximation thereof for @code{order=2}),
and simulated contemporaneous correlations otherwise. The variables are arranged in declaration order.
@end defvr
@defvr {MATLAB/Octave variable} oo_.irfs
After a run of @code{stoch_simul} with option @code{irf} different
from zero, contains the impulse responses, with the following naming
@ -5380,6 +5402,10 @@ variables. Results are stored in
@code{oo_.PosteriorTheoreticalMoments} (@pxref{oo_.PosteriorTheoreticalMoments}). The number of lags in the autocorrelation function is
controlled by the @code{ar} option.
@item contemporaneous_correlation
@xref{contemporaneous_correlation}. Results are stored in @code{oo_.PosteriorTheoreticalMoments}.
Note that the @code{nocorr}-option has no effect.
@item conditional_variance_decomposition = @var{INTEGER}
See below.
@ -5924,6 +5950,9 @@ where @var{THEORETICAL_MOMENT} is one of the following:
@item covariance
Variance-covariance of endogenous variables
@item contemporaneous_correlation
Contemporaneous correlation of endogenous variables when the @ref{contemporaneous_correlation} option is specified.
@item correlation
Auto- and cross-correlation of endogenous variables. Fields are vectors with correlations from 1 up to order @code{options_.ar}

5
matlab/compute_moments_varendo.m
View File

@ -33,6 +33,9 @@ function oo_ = compute_moments_varendo(type,options_,M_,oo_,var_list_)
% You should have received a copy of the GNU General Public License
% along with Dynare. If not, see <http://www.gnu.org/licenses/>.
fprintf('Estimation::compute_moments_varendo: I''m computing endogenous moments (this may take a while)... ');
if strcmpi(type,'posterior')
posterior = 1;
if nargin==4
@ -126,3 +129,5 @@ if M_.exo_nbr > 1
end
end
end
fprintf(' Done!\n');

28
matlab/covariance_mc_analysis.m
View File

@ -1,4 +1,4 @@
function oo_ = covariance_mc_analysis(NumberOfSimulations,type,dname,fname,vartan,nvar,var1,var2,mh_conf_sig,oo_)
function oo_ = covariance_mc_analysis(NumberOfSimulations,type,dname,fname,vartan,nvar,var1,var2,mh_conf_sig,oo_,options_)
% This function analyses the (posterior or prior) distribution of the
% endogenous variables' covariance matrix.
%
@ -14,6 +14,7 @@ function oo_ = covariance_mc_analysis(NumberOfSimulations,type,dname,fname,varta
% mh_conf_sig [double] 2 by 1 vector with upper
% and lower bound of HPD intervals
% oo_ [structure] Dynare structure where the results are saved.
% options_ [structure] Dynare options structure
%
% OUTPUTS
% oo_ [structure] Dynare structure where the results are saved.
@ -86,10 +87,21 @@ end
ListOfFiles = dir([ PATH fname '_' TYPE '2ndOrderMoments*.mat']);
i1 = 1; tmp = zeros(NumberOfSimulations,1);
if options_.contemporaneous_correlation
tmp_corr_mat = zeros(NumberOfSimulations,1);
cov_pos=symmetric_matrix_index(indx1,indx2,nvar);
var_pos_1=symmetric_matrix_index(indx1,indx1,nvar);
var_pos_2=symmetric_matrix_index(indx2,indx2,nvar);
end
for file = 1:length(ListOfFiles)
load([ PATH ListOfFiles(file).name ]);
i2 = i1 + rows(Covariance_matrix) - 1;
tmp(i1:i2) = Covariance_matrix(:,symmetric_matrix_index(indx1,indx2,nvar));
if options_.contemporaneous_correlation
temp=Covariance_matrix(:,cov_pos)./(sqrt(Covariance_matrix(:,var_pos_1)).*sqrt(Covariance_matrix(:,var_pos_2)));
temp(Covariance_matrix(:,cov_pos)==0)=0; %filter out 0 correlations that would result in 0/0
tmp_corr_mat(i1:i2)=temp;
end
i1 = i2+1;
end
name = [var1 '.' var2];
@ -111,4 +123,16 @@ else
eval(['oo_.' TYPE 'TheoreticalMoments.dsge.covariance.HPDsup.' name ' = NaN;']);
eval(['oo_.' TYPE 'TheoreticalMoments.dsge.covariance.deciles.' name ' = NaN;']);
eval(['oo_.' TYPE 'TheoreticalMoments.dsge.covariance.density.' name ' = NaN;']);
end
end
if options_.contemporaneous_correlation
[p_mean, p_median, p_var, hpd_interval, p_deciles, density] = ...
posterior_moments(tmp_corr_mat,1,mh_conf_sig);
eval(['oo_.' TYPE 'TheoreticalMoments.dsge.contemporeaneous_correlation.Mean.' name ' = p_mean;']);
eval(['oo_.' TYPE 'TheoreticalMoments.dsge.contemporeaneous_correlation.Median.' name ' = p_median;']);
eval(['oo_.' TYPE 'TheoreticalMoments.dsge.contemporeaneous_correlation.Variance.' name ' = p_var;']);
eval(['oo_.' TYPE 'TheoreticalMoments.dsge.contemporeaneous_correlation.HPDinf.' name ' = hpd_interval(1);']);
eval(['oo_.' TYPE 'TheoreticalMoments.dsge.contemporeaneous_correlation.HPDsup.' name ' = hpd_interval(2);']);
eval(['oo_.' TYPE 'TheoreticalMoments.dsge.contemporeaneous_correlation.deciles.' name ' = p_deciles;']);
eval(['oo_.' TYPE 'TheoreticalMoments.dsge.contemporeaneous_correlation.density.' name ' = density;']);
end

3
matlab/disp_moments.m
View File

@ -69,6 +69,9 @@ end
if options_.nocorr == 0
corr = (y'*y/size(y,1))./(s'*s);
if options_.contemporaneous_correlation
oo_.contemporaneous_correlation = corr;
end
if options_.noprint == 0
title = 'CORRELATION OF SIMULATED VARIABLES';
if options_.hp_filter

3
matlab/disp_th_moments.m
View File

@ -117,6 +117,9 @@ end
if options_.nocorr == 0 && size(stationary_vars, 1) > 0
corr = oo_.gamma_y{1}(i1,i1)./(sd(i1)*sd(i1)');
if options_.contemporaneous_correlation
oo_.contemporaneous_correlation = corr;
end
if ~options_.noprint,
skipline()
if options_.order == 2

1
matlab/global_initialization.m
View File

@ -480,6 +480,7 @@ end
options_.filter_covariance = 0;
options_.filter_decomposition = 0;
options_.selected_variables_only = 0;
options_.contemporaneous_correlation = 0;
options_.initialize_estimated_parameters_with_the_prior_mode = 0;
options_.estimation_dll = 0;
% Misc

2
matlab/posterior_analysis.m
View File

@ -55,7 +55,7 @@ switch type
dsge_simulated_theoretical_covariance(SampleSize,M_,options_,oo_,'posterior');
end
oo_ = covariance_mc_analysis(SampleSize,'posterior',M_.dname,M_.fname,...
vartan,nvar,arg1,arg2,options_.mh_conf_sig,oo_);
vartan,nvar,arg1,arg2,options_.mh_conf_sig,oo_,options_);
case 'decomposition'
if nargin==narg1
[nvar,vartan,NumberOfFiles] = ...

2
matlab/prior_analysis.m
View File

@ -56,7 +56,7 @@ switch type
dsge_simulated_theoretical_covariance(SampleSize,M_,options_,oo_,'prior');
end
oo_ = covariance_mc_analysis(SampleSize,'prior',M_.dname,M_.fname,...
vartan,nvar,arg1,arg2,options_.mh_conf_sig,oo_);
vartan,nvar,arg1,arg2,options_.mh_conf_sig,oo_,options_);
case 'decomposition'
if nargin==narg1
[nvar,vartan,NumberOfFiles] = ...

5
preprocessor/DynareBison.yy
View File

@ -106,7 +106,7 @@ class ParsingDriver;
%token LYAPUNOV_FIXED_POINT_TOL LYAPUNOV_DOUBLING_TOL LYAPUNOV_SQUARE_ROOT_SOLVER_TOL LOG_DEFLATOR LOG_TREND_VAR LOG_GROWTH_FACTOR MARKOWITZ MARGINAL_DENSITY MAX MAXIT
%token MFS MH_CONF_SIG MH_DROP MH_INIT_SCALE MH_JSCALE MH_MODE MH_NBLOCKS MH_REPLIC MH_RECOVER POSTERIOR_MAX_SUBSAMPLE_DRAWS MIN MINIMAL_SOLVING_PERIODS
%token MODE_CHECK MODE_CHECK_NEIGHBOURHOOD_SIZE MODE_CHECK_SYMMETRIC_PLOTS MODE_CHECK_NUMBER_OF_POINTS MODE_COMPUTE MODE_FILE MODEL MODEL_COMPARISON MODEL_INFO MSHOCKS ABS SIGN
%token MODEL_DIAGNOSTICS MODIFIEDHARMONICMEAN MOMENTS_VARENDO DIFFUSE_FILTER SUB_DRAWS TAPER_STEPS GEWEKE_INTERVAL MCMC_JUMPING_COVARIANCE MOMENT_CALIBRATION
%token MODEL_DIAGNOSTICS MODIFIEDHARMONICMEAN MOMENTS_VARENDO CONTEMPORANEOUS_CORRELATION DIFFUSE_FILTER SUB_DRAWS TAPER_STEPS GEWEKE_INTERVAL MCMC_JUMPING_COVARIANCE MOMENT_CALIBRATION
%token NUMBER_OF_PARTICLES RESAMPLING SYSTEMATIC GENERIC RESAMPLING_THRESHOLD RESAMPLING_METHOD KITAGAWA STRATIFIED SMOOTH
%token FILTER_ALGORITHM PROPOSAL_APPROXIMATION CUBATURE UNSCENTED MONTECARLO DISTRIBUTION_APPROXIMATION
%token <string_val> NAME
@ -1068,6 +1068,7 @@ stoch_simul_primary_options : o_dr_algo
| o_drop
| o_ar
| o_nocorr
| o_contemporaneous_correlation
| o_nofunctions
| o_nomoments
| o_nograph
@ -1672,6 +1673,7 @@ estimation_options : o_datafile
| o_forecast
| o_smoother
| o_moments_varendo
| o_contemporaneous_correlation
| o_filtered_vars
| o_kalman_algo
| o_kalman_tol
@ -2706,6 +2708,7 @@ o_tex : TEX { driver.option_num("TeX", "1"); };
o_forecast : FORECAST EQUAL INT_NUMBER { driver.option_num("forecast", $3); };
o_smoother : SMOOTHER { driver.option_num("smoother", "1"); };
o_moments_varendo : MOMENTS_VARENDO { driver.option_num("moments_varendo", "1"); };
o_contemporaneous_correlation : CONTEMPORANEOUS_CORRELATION { driver.option_num("contemporaneous_correlation", "1"); };
o_filtered_vars : FILTERED_VARS { driver.option_num("filtered_vars", "1"); };
o_relative_irf : RELATIVE_IRF { driver.option_num("relative_irf", "1"); };
o_kalman_algo : KALMAN_ALGO EQUAL INT_NUMBER { driver.option_num("kalman_algo", $3); };

1
preprocessor/DynareFlex.ll
View File

@ -298,6 +298,7 @@ DATE -?[0-9]+([YyAa]|[Mm]([1-9]|1[0-2])|[Qq][1-4]|[Ww]([1-9]{1}|[1-4][0-9]|5[0-2
<DYNARE_STATEMENT>dsge_var {return token::DSGE_VAR;}
<DYNARE_STATEMENT>dsge_varlag {return token::DSGE_VARLAG;}
<DYNARE_STATEMENT>moments_varendo {return token::MOMENTS_VARENDO;}
<DYNARE_STATEMENT>contemporaneous_correlation {return token::CONTEMPORANEOUS_CORRELATION;}
<DYNARE_STATEMENT>posterior_max_subsample_draws {return token::POSTERIOR_MAX_SUBSAMPLE_DRAWS;}
<DYNARE_STATEMENT>filtered_vars {return token::FILTERED_VARS;}
<DYNARE_STATEMENT>filter_step_ahead {return token::FILTER_STEP_AHEAD;}

6
tests/TeX/fs2000_corr_ME.mod
View File

@ -123,7 +123,7 @@ end;
steady;
stoch_simul(order=1,irf=20,graph_format=eps);
stoch_simul(order=1,irf=20,graph_format=eps,contemporaneous_correlation);
write_latex_original_model;
write_latex_static_model;
@ -143,7 +143,7 @@ stderr gy_obs, 1;
corr gp_obs, gy_obs,0;
end;
estimation(order=1,datafile='../fs2000/fsdat_simul',mode_check,smoother,filter_decomposition,forecast = 8,filtered_vars,filter_step_ahead=[1,3],irf=20) m P c e W R k d y gy_obs;
estimation(order=1,datafile='../fs2000/fsdat_simul',mode_check,smoother,filter_decomposition,forecast = 8,filtered_vars,filter_step_ahead=[1,3],irf=20,contemporaneous_correlation) m P c e W R k d y gy_obs;
@ -159,7 +159,7 @@ stderr gp_obs, inv_gamma_pdf, 0.001, inf;
//corr gp_obs, gy_obs,normal_pdf, 0, 0.2;
end;
estimation(mode_compute=9,order=1,datafile='../fs2000/fsdat_simul',mode_check,smoother,filter_decomposition,mh_replic=2002, mh_nblocks=2, mh_jscale=0.8,forecast = 8,bayesian_irf,filtered_vars,filter_step_ahead=[1,3],irf=20,moments_varendo) m P c e W R k d y;
estimation(mode_compute=9,order=1,datafile='../fs2000/fsdat_simul',mode_check,smoother,filter_decomposition,mh_replic=2002, mh_nblocks=2, mh_jscale=0.8,forecast = 8,bayesian_irf,filtered_vars,filter_step_ahead=[1,3],irf=20,moments_varendo,contemporaneous_correlation) m P c e W R k d y;
shock_decomposition y W R;
collect_LaTeX_Files(M_);