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

modification of the sufficient statistics in the auxiliary particle filter

remove-submodule^2
Frédéric Karamé 2015-01-07 13:49:33 +01:00
parent ae021c7871
commit 056be5f37d
1 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
nonlinear-filters/src/auxiliary_particle_filter.m
View File

@ -98,13 +98,21 @@ else
end
StateVectors = tmp(mf0,:) ;
%[nodes,nodes_weights] = spherical_radial_sigma_points(number_of_structural_innovations) ;
[nodes,nodes_weights,nodes_weights_c] = unscented_sigma_points(number_of_structural_innovations,ParticleOptions);
nodes = Q_lower_triangular_cholesky*nodes ;
for t=1:sample_size
yhat = bsxfun(@minus,StateVectors,state_variables_steady_state);
if pruning
yhat_ = bsxfun(@minus,StateVectors_,state_variables_steady_state);
[tmp, tmp_] = local_state_space_iteration_2(yhat,zeros(number_of_structural_innovations,number_of_particles),ghx,ghu,constant,ghxx,ghuu,ghxu,yhat_,steadystate,ThreadsOptions.local_state_space_iteration_2);
else
tmp = local_state_space_iteration_2(yhat,zeros(number_of_structural_innovations,number_of_particles),ghx,ghu,constant,ghxx,ghuu,ghxu,ThreadsOptions.local_state_space_iteration_2);
% if pruning
% yhat_ = bsxfun(@minus,StateVectors_,state_variables_steady_state);
% [tmp, tmp_] = local_state_space_iteration_2(yhat,zeros(number_of_structural_innovations,number_of_particles),ghx,ghu,constant,ghxx,ghuu,ghxu,yhat_,steadystate,ThreadsOptions.local_state_space_iteration_2);
% else
% tmp = local_state_space_iteration_2(yhat,zeros(number_of_structural_innovations,number_of_particles),ghx,ghu,constant,ghxx,ghuu,ghxu,ThreadsOptions.local_state_space_iteration_2);
% end
tmp = 0 ;
for i=1:size(nodes)
tmp = tmp + nodes_weights*local_state_space_iteration_2(yhat,nodes(i,:)*ones(1,number_of_particles),ghx,ghu,constant,ghxx,ghuu,ghxu,ThreadsOptions.local_state_space_iteration_2);
end
PredictedObservedMean = weights*(tmp(mf1,:)');
PredictionError = bsxfun(@minus,Y(:,t),tmp(mf1,:));