Updated version following new revision of dsgelikelihood.m

git-svn-id: https://www.dynare.org/svn/dynare/trunk@3318 ac1d8469-bf42-47a9-8791-bf33cf982152

matlab/DsgeLikelihood_hh.m

@@ -1,4 +1,4 @@
-function [fval,llik,cost_flag,ys,trend_coeff,info] = DsgeLikelihood_hh(xparam1,gend,data,data_index,number_of_observations,no_more_missing_observations)
+function [fval,llik,cost_flag,ys,trend_coeff,info] = DsgeLikelihood(xparam1,gend,data,data_index,number_of_observations,no_more_missing_observations)
 % function [fval,cost_flag,ys,trend_coeff,info] = DsgeLikelihood(xparam1,gend,data,data_index,number_of_observations,no_more_missing_observations)
 % Evaluates the posterior kernel of a dsge model. 
 % 
@@ -42,9 +42,9 @@ global bayestopt_ estim_params_ options_ trend_coeff_ M_ oo_
   fval		= [];
   ys		= [];
   trend_coeff	= [];
-llik = NaN;
   cost_flag  	= 1;
   nobs 		= size(options_.varobs,1);
+  llik=NaN;
   %------------------------------------------------------------------------------
   % 1. Get the structural parameters & define penalties
   %------------------------------------------------------------------------------
@@ -128,26 +128,26 @@ M_.H = H;
   [T,R,SteadyState,info] = dynare_resolve(bayestopt_.restrict_var_list,...
 					  bayestopt_.restrict_columns,...
 					  bayestopt_.restrict_aux);
-if info(1) == 1 | info(1) == 2 | info(1) == 5
+  if info(1) == 1 || info(1) == 2 || info(1) == 5
       fval = bayestopt_.penalty+1;
       cost_flag = 0;
       return
-elseif info(1) == 3 | info(1) == 4 | info(1) == 20
+  elseif info(1) == 3 || info(1) == 4 || info(1)==6 ||info(1) == 19 || info(1) == 20 || info(1) == 21
-    fval = bayestopt_.penalty+info(2);%^2; % penalty power raised in DR1.m and resol already. GP July'08
+      fval = bayestopt_.penalty+info(2);
       cost_flag = 0;
       return
   end
   bayestopt_.mf = bayestopt_.mf1;
-if ~options_.noconstant
+  if options_.noconstant
-    if options_.loglinear == 1
+      constant = zeros(nobs,1);  
+  else    
+      if options_.loglinear
           constant = log(SteadyState(bayestopt_.mfys));
       else
           constant = SteadyState(bayestopt_.mfys);
       end
-else
-    constant = zeros(nobs,1);
   end
-if bayestopt_.with_trend == 1
+  if bayestopt_.with_trend
     trend_coeff = zeros(nobs,1);
     t = options_.trend_coeffs;
     for i=1:length(t)
@@ -242,16 +242,6 @@ elseif options_.lik_init == 3   % Diffuse Kalman filter
       end
   end
   if kalman_algo == 2
-    no_correlation_flag = 1;
-    if length(H)==1
-        H = zeros(nobs,1);
-    else
-        if all(all(abs(H-diag(diag(H)))<1e-14))% ie, the covariance matrix is diagonal...
-            H = diag(H);
-        else
-            no_correlation_flag = 1;
-        end
-    end
   end
   kalman_tol = options_.kalman_tol;
   riccati_tol = options_.riccati_tol;
@@ -273,6 +263,16 @@ if (kalman_algo==1)% Multivariate Kalman Filter
       end
   end
   if (kalman_algo==2)% Univariate Kalman Filter
+      no_correlation_flag = 1;
+      if length(H)==1 & H == 0
+          H = zeros(nobs,1);
+      else
+          if all(all(abs(H-diag(diag(H)))<1e-14))% ie, the covariance matrix is diagonal...
+              H = diag(H);
+          else
+              no_correlation_flag = 0;
+          end
+      end
       if no_correlation_flag
           [LIK, lik] = univariate_kalman_filter(T,R,Q,H,Pstar,Y,start,mf,kalman_tol,riccati_tol,data_index,number_of_observations,no_more_missing_observations);
       else
@@ -281,29 +281,38 @@ if (kalman_algo==2)% Univariate Kalman Filter
   end
   if (kalman_algo==3)% Multivariate Diffuse Kalman Filter
       if no_missing_data_flag
-        data1 = data - trend;
+          [LIK, lik] = diffuse_kalman_filter(ST,R1,Q,H,Pinf,Pstar,Y,start,Z,kalman_tol, ...
-        if any(any(H ~= 0))
+                                      riccati_tol);
-            [LIK, lik] = DiffuseLikelihoodH1_Z(ST,Z,R1,Q,H,Pinf,Pstar,data1,start);
       else
-            [LIK, lik] = DiffuseLikelihood1_Z(ST,Z,R1,Q,Pinf,Pstar,data1,start);
+          [LIK, lik] = missing_observations_diffuse_kalman_filter(ST,R1,Q,H,Pinf, ...
+                                                           Pstar,Y,start,Z,kalman_tol,riccati_tol,...
+                                                           data_index,number_of_observations,...
+                                                           no_more_missing_observations);
       end
       if isinf(LIK)
           kalman_algo = 4;
       end
-    else
-        error(['The diffuse filter is not yet implemented for models with missing observations'])
-    end
   end
   if (kalman_algo==4)% Univariate Diffuse Kalman Filter
-    data1 = data - trend;
+      no_correlation_flag = 1;
-    if any(any(H ~= 0))
+      if length(H)==1 & H == 0
-        if ~estim_params_.ncn 
+          H = zeros(nobs,1);
-            [LIK, lik] = DiffuseLikelihoodH3_Z(ST,Z,R1,Q,H,Pinf,Pstar,data1,trend,start);
       else
-            [LIK, lik] = DiffuseLikelihoodH3corr_Z(ST,Z,R1,Q,H,Pinf,Pstar,data1,trend,start);
+          if all(all(abs(H-diag(diag(H)))<1e-14))% ie, the covariance matrix is diagonal...
+              H = diag(H);
+          else
+              no_correlation_flag = 0;
           end
+      end
+      if no_correlation_flag
+          [LIK, lik] = univariate_diffuse_kalman_filter(ST,R1,Q,H,Pinf,Pstar,Y, ...
+                                                 start,Z,kalman_tol,riccati_tol,data_index,...
+                                                 number_of_observations,no_more_missing_observations);
       else
-        [LIK, lik] = DiffuseLikelihood3_Z(ST,Z,R1,Q,Pinf,Pstar,data1,start);
+          [LIK, lik] = univariate_diffuse_kalman_filter_corr(ST,R1,Q,H,Pinf,Pstar, ...
+                                                      Y,start,Z,kalman_tol,riccati_tol,...
+                                                      data_index,number_of_observations,...
+                                                      no_more_missing_observations);
       end
   end
   if imag(LIK) ~= 0