New version of get_companion_matrix + new integration test.

The routine is still buggy. In PAC and VAR_EXPECTATION models we
use get_companion_matrix_legacy routine instead.
time-shift
Stéphane Adjemian(Charybdis) 2018-09-19 17:20:29 +02:00
parent c588544b13
commit 031e2c87c6
Signed by untrusted user who does not match committer: stepan
GPG Key ID: A6D44CB9C64CE77B
28 changed files with 926 additions and 874 deletions

View File

@ -39,4 +39,4 @@ end
M_.pac.(pacmodel).auxiliary_model_type = auxiliary_model_type;
get_companion_matrix(auxiliary_model_name, auxiliary_model_type);
get_companion_matrix_legacy(auxiliary_model_name, auxiliary_model_type);

View File

@ -59,7 +59,7 @@ auxcalib = DynareOutput.(varexpectationmodel.auxiliary_model_type).(varexpectati
if ~isfield(auxcalib, 'CompanionMatrix') || any(isnan(auxcalib.CompanionMatrix(:)))
message = sprintf('Auxiliary model %s has to be estimated first.', varexpectationmodel.auxiliary_model_name);
message = sprintf('%s\nPlease use get_companion_matrix command first.', message);
message = sprintf('%s\nPlease use *get_companion_matrix command first.', message);
error(message);
end

View File

@ -42,4 +42,4 @@ end
M_.var_expectation.(varexpectationmodel).auxiliary_model_type = auxiliary_model_type;
get_companion_matrix(auxiliary_model_name, auxiliary_model_type);
get_companion_matrix_legacy(auxiliary_model_name, auxiliary_model_type);

View File

@ -31,7 +31,7 @@ function [A0, AR, B] = get_companion_matrix(auxiliary_model_name, auxiliary_mode
global oo_ M_
if nargin<2
if nargin < 2
if isfield(M_, 'var') && isfield(M_.var, auxiliary_model_name)
auxiliary_model_type = 'var';
elseif isfield(M_, 'trend_component') && isfield(M_.trend_component, auxiliary_model_name)
@ -41,39 +41,47 @@ if nargin<2
end
end
if nargout
A0 = [];
AR = [];
B = [];
if strcmp(auxiliary_model_type, 'var')
AR = evalin('base', [M_.fname '.var_ar(''' auxiliary_model_name ''', M_.params)']);
elseif strcmp(auxiliary_model_type, 'trend_component')
[AR, A0] = evalin('base', [M_.fname '.trend_component_ar_ec(''' auxiliary_model_name ''', M_.params)']);
else
error('Unknown type of auxiliary model.')
end
get_ar_ec_matrices(auxiliary_model_name, auxiliary_model_type);
% Get the number of lags
p = size(oo_.(auxiliary_model_type).(auxiliary_model_name).ar, 3);
p = size(AR, 3);
% Get the number of variables
n = length(oo_.(auxiliary_model_type).(auxiliary_model_name).ar(:,:,1));
n = length(M_.(auxiliary_model_type).(auxiliary_model_name).lhs);
switch auxiliary_model_type
case 'var'
oo_.var.(auxiliary_model_name).CompanionMatrix = zeros(n*p);
oo_.var.(auxiliary_model_name).CompanionMatrix(1:n,1:n) = oo_.var.(auxiliary_model_name).ar(:,:,1);
for i=2:p
oo_.var.(auxiliary_model_name).CompanionMatrix(1:n,(i-1)*n+(1:n)) = oo_.var.(auxiliary_model_name).ar(:,:,i);
oo_.var.(auxiliary_model_name).CompanionMatrix(1:n,1:n) = AR(:,:,1);
for i = 2:p
oo_.var.(auxiliary_model_name).CompanionMatrix(1:n,(i-1)*n+(1:n)) = AR(:,:,i);
oo_.var.(auxiliary_model_name).CompanionMatrix((i-1)*n+(1:n),(i-2)*n+(1:n)) = eye(n);
end
M_.var.(auxiliary_model_name).list_of_variables_in_companion_var = M_.endo_names(M_.var.(auxiliary_model_name).lhs);
if nargout
A0 = [];
B = [];
end
case 'trend_component'
% Get number of trends.
q = sum(M_.trend_component.(auxiliary_model_name).trends);
% Get the number of equations with error correction.
m = n-q;
m = n - q;
% Get the indices of trend and EC equations in the auxiliary model.
trend_eqnums_in_auxiliary_model = find(M_.trend_component.(auxiliary_model_name).trends);
ecm_eqnums_in_auxiliary_model = find(~M_.trend_component.(auxiliary_model_name).trends);
% Get the indices of trend equations in model.
trend_eqnums = M_.trend_component.(auxiliary_model_name).trend_eqn;
% REMARK It is assumed that the non trend equations are the error correction
% equations. We assume that the model can be cast in the following form:
%
@ -99,68 +107,71 @@ switch auxiliary_model_type
%
% where the dimensions of I and 0 matrices can easily be
% deduced from the number of EC and trend equations.
% Check that the lhs of candidate ecm equations are at least first differences.
for i=1:m
for i = 1:m
if ~get_difference_order(M_.trend_component.(auxiliary_model_name).lhs(ecm_eqnums_in_auxiliary_model(i)))
error('Model %s is not a Trend component model! LHS variables should be in difference', auxiliary_model_name)
error([auxiliary_model_name ' is not a trend component model. The LHS variables should be in differences'])
end
end
% Get the trend variables indices (lhs variables in trend equations).
[~, id_trend_in_var, ~] = intersect(M_.trend_component.(auxiliary_model_name).eqn, trend_eqnums);
trend_variables = reshape(M_.trend_component.(auxiliary_model_name).lhs(id_trend_in_var), q, 1);
% Get the rhs variables in trend equations.
trend_autoregressive_variables = zeros(q, 1);
for i=1:q
for i = 1:q
% Check that there is only one variable on the rhs and update trend_autoregressive_variables.
v = M_.trend_component.(auxiliary_model_name).rhs.vars_at_eq{id_trend_in_var(i)}.var;
if length(v)~=1
if length(v) ~= 1
error('A trend equation (%s) must have only one variable on the RHS!', M_.trend_component.(auxiliary_model_name).eqtags{trend_eqnums(i)})
end
trend_autoregressive_variables(i) = v;
% Check that the variables on lhs and rhs have the same difference orders.
if get_difference_order(trend_variables(i))~=get_difference_order(trend_autoregressive_variables(i))
if get_difference_order(trend_variables(i)) ~= get_difference_order(v)
error('In a trend equation (%s) LHS and RHS variables must have the same difference orders!', M_.trend_component.(auxiliary_model_name).eqtags{trend_eqnums(i)})
end
% Check that the trend equation is autoregressive.
if isdiff(v)
if ~M_.aux_vars(get_aux_variable_id(v)).type==9
if ~M_.aux_vars(get_aux_variable_id(v)).type == 9
error('In a trend equation (%s) RHS variable must be lagged LHS variable!', M_.trend_component.(auxiliary_model_name).eqtags{trend_eqnums(i)})
else
if M_.aux_vars(get_aux_variable_id(v)).orig_index~=trend_variables(i)
if M_.aux_vars(get_aux_variable_id(v)).orig_index ~= trend_variables(i)
error('In a trend equation (%s) RHS variable must be lagged LHS variable!', M_.trend_component.(auxiliary_model_name).eqtags{trend_eqnums(i)})
end
end
else
if get_aux_variable_id(v) && M_.aux_vars(get_aux_variable_id(v)).endo_index~=trend_variables(i)
if get_aux_variable_id(v) && M_.aux_vars(get_aux_variable_id(v)).endo_index ~= trend_variables(i)
error('In a trend equation (%s) RHS variable must be lagged LHS variable!', M_.trend_component.(auxiliary_model_name).eqtags{trend_eqnums(i)})
end
end
end
% Reorder trend_eqnums_in_auxiliary_model to ensure that the order of
% the trend variables matches the order of the error correction
% variables.
[~,reorder] = ismember(M_.trend_component.toto.lhs(trend_eqnums_in_auxiliary_model), ...
M_.trend_component.toto.trend_vars(find(M_.trend_component.toto.trend_vars>0)));
M_.trend_component.toto.trend_vars(M_.trend_component.toto.trend_vars > 0));
trend_eqnums_in_auxiliary_model = trend_eqnums_in_auxiliary_model(reorder);
% Get the EC matrix (the EC term is assumend to be in t-1).
%
% TODO: Check that the EC term is the difference between the
% endogenous variable and the trend variable.
%
A0 = oo_.trend_component.(auxiliary_model_name).ec(ecm_eqnums_in_auxiliary_model,:,1);
% Get the AR matrices.
AR = oo_.trend_component.(auxiliary_model_name).ar(ecm_eqnums_in_auxiliary_model,ecm_eqnums_in_auxiliary_model,:);
% Build B matrices (VAR in levels)
B(ecm_eqnums_in_auxiliary_model,ecm_eqnums_in_auxiliary_model,1) = eye(m)+A0+AR(:,:,1);
B(ecm_eqnums_in_auxiliary_model,trend_eqnums_in_auxiliary_model) = -A0;
B(trend_eqnums_in_auxiliary_model,trend_eqnums_in_auxiliary_model) = eye(q);
for i=2:p
B(ecm_eqnums_in_auxiliary_model,ecm_eqnums_in_auxiliary_model,i) = AR(:,:,i)-AR(:,:,i-1);
B(ecm_eqnums_in_auxiliary_model, ecm_eqnums_in_auxiliary_model, 1) = eye(m) + A0 + AR(:,:,1);
B(ecm_eqnums_in_auxiliary_model, trend_eqnums_in_auxiliary_model) = -A0;
B(trend_eqnums_in_auxiliary_model, trend_eqnums_in_auxiliary_model) = eye(q);
for i = 2:p
B(ecm_eqnums_in_auxiliary_model,ecm_eqnums_in_auxiliary_model,i) = AR(:,:,i) - AR(:,:,i-1);
end
B(ecm_eqnums_in_auxiliary_model,ecm_eqnums_in_auxiliary_model,p+1) = -AR(:,:,p);
% Write Companion matrix
oo_.trend_component.(auxiliary_model_name).CompanionMatrix = zeros(size(B, 1)*size(B, 3));
for i=1:p
for i = 1:p
oo_.trend_component.(auxiliary_model_name).CompanionMatrix(1:n, (i-1)*n+(1:n)) = B(:,:,i);
oo_.trend_component.(auxiliary_model_name).CompanionMatrix(i*n+(1:n),(i-1)*n+(1:n)) = eye(n);
end

View File

@ -1,6 +1,5 @@
function [A0, AR, B] = get_companion_matrix_preprocessor(auxiliary_model_name, auxiliary_model_type)
%function [A0, AR, B] = get_companion_matrix_preprocessor(auxiliary_model_name, auxiliary_model_type)
%
function [A0, AR, B] = get_companion_matrix_legacy(auxiliary_model_name, auxiliary_model_type)
% Gets the companion VAR representation of a PAC auxiliary model.
% Depending on the nature of this auxiliary model the output is
% saved in oo_.{var,trend_component}.(auxiliary_model_name).CompanionMatrix
@ -32,7 +31,7 @@ function [A0, AR, B] = get_companion_matrix_preprocessor(auxiliary_model_name, a
global oo_ M_
if nargin < 2
if nargin<2
if isfield(M_, 'var') && isfield(M_.var, auxiliary_model_name)
auxiliary_model_type = 'var';
elseif isfield(M_, 'trend_component') && isfield(M_.trend_component, auxiliary_model_name)
@ -42,47 +41,39 @@ if nargin < 2
end
end
if strcmp(auxiliary_model_type, 'var')
AR = evalin('base', [M_.fname '.var_ar(''' auxiliary_model_name ''', M_.params)']);
elseif strcmp(auxiliary_model_type, 'trend_component')
[AR, A0] = evalin('base', [M_.fname '.trend_component_ar_ec(''' auxiliary_model_name ''', M_.params)']);
else
error('Unknown type of auxiliary model.')
if nargout
A0 = [];
AR = [];
B = [];
end
get_ar_ec_matrices(auxiliary_model_name, auxiliary_model_type);
% Get the number of lags
p = size(AR, 3);
p = size(oo_.(auxiliary_model_type).(auxiliary_model_name).ar, 3);
% Get the number of variables
n = length(M_.(auxiliary_model_type).(auxiliary_model_name).lhs);
n = length(oo_.(auxiliary_model_type).(auxiliary_model_name).ar(:,:,1));
switch auxiliary_model_type
case 'var'
oo_.var.(auxiliary_model_name).CompanionMatrix = zeros(n*p);
oo_.var.(auxiliary_model_name).CompanionMatrix(1:n,1:n) = AR(:,:,1);
for i = 2:p
oo_.var.(auxiliary_model_name).CompanionMatrix(1:n,(i-1)*n+(1:n)) = AR(:,:,i);
oo_.var.(auxiliary_model_name).CompanionMatrix(1:n,1:n) = oo_.var.(auxiliary_model_name).ar(:,:,1);
for i=2:p
oo_.var.(auxiliary_model_name).CompanionMatrix(1:n,(i-1)*n+(1:n)) = oo_.var.(auxiliary_model_name).ar(:,:,i);
oo_.var.(auxiliary_model_name).CompanionMatrix((i-1)*n+(1:n),(i-2)*n+(1:n)) = eye(n);
end
M_.var.(auxiliary_model_name).list_of_variables_in_companion_var = M_.endo_names(M_.var.(auxiliary_model_name).lhs);
if nargout
A0 = [];
B = [];
end
case 'trend_component'
% Get number of trends.
q = sum(M_.trend_component.(auxiliary_model_name).trends);
% Get the number of equations with error correction.
m = n - q;
m = n-q;
% Get the indices of trend and EC equations in the auxiliary model.
trend_eqnums_in_auxiliary_model = find(M_.trend_component.(auxiliary_model_name).trends);
ecm_eqnums_in_auxiliary_model = find(~M_.trend_component.(auxiliary_model_name).trends);
% Get the indices of trend equations in model.
trend_eqnums = M_.trend_component.(auxiliary_model_name).trend_eqn;
% REMARK It is assumed that the non trend equations are the error correction
% equations. We assume that the model can be cast in the following form:
%
@ -108,71 +99,68 @@ switch auxiliary_model_type
%
% where the dimensions of I and 0 matrices can easily be
% deduced from the number of EC and trend equations.
% Check that the lhs of candidate ecm equations are at least first differences.
for i = 1:m
for i=1:m
if ~get_difference_order(M_.trend_component.(auxiliary_model_name).lhs(ecm_eqnums_in_auxiliary_model(i)))
error([auxiliary_model_name ' is not a trend component model. The LHS variables should be in differences'])
error('Model %s is not a Trend component model! LHS variables should be in difference', auxiliary_model_name)
end
end
% Get the trend variables indices (lhs variables in trend equations).
[~, id_trend_in_var, ~] = intersect(M_.trend_component.(auxiliary_model_name).eqn, trend_eqnums);
trend_variables = reshape(M_.trend_component.(auxiliary_model_name).lhs(id_trend_in_var), q, 1);
% Get the rhs variables in trend equations.
for i = 1:q
trend_autoregressive_variables = zeros(q, 1);
for i=1:q
% Check that there is only one variable on the rhs and update trend_autoregressive_variables.
v = M_.trend_component.(auxiliary_model_name).rhs.vars_at_eq{id_trend_in_var(i)}.var;
if length(v) ~= 1
if length(v)~=1
error('A trend equation (%s) must have only one variable on the RHS!', M_.trend_component.(auxiliary_model_name).eqtags{trend_eqnums(i)})
end
trend_autoregressive_variables(i) = v;
% Check that the variables on lhs and rhs have the same difference orders.
if get_difference_order(trend_variables(i)) ~= get_difference_order(v)
if get_difference_order(trend_variables(i))~=get_difference_order(trend_autoregressive_variables(i))
error('In a trend equation (%s) LHS and RHS variables must have the same difference orders!', M_.trend_component.(auxiliary_model_name).eqtags{trend_eqnums(i)})
end
% Check that the trend equation is autoregressive.
if isdiff(v)
if ~M_.aux_vars(get_aux_variable_id(v)).type == 9
if ~M_.aux_vars(get_aux_variable_id(v)).type==9
error('In a trend equation (%s) RHS variable must be lagged LHS variable!', M_.trend_component.(auxiliary_model_name).eqtags{trend_eqnums(i)})
else
if M_.aux_vars(get_aux_variable_id(v)).orig_index ~= trend_variables(i)
if M_.aux_vars(get_aux_variable_id(v)).orig_index~=trend_variables(i)
error('In a trend equation (%s) RHS variable must be lagged LHS variable!', M_.trend_component.(auxiliary_model_name).eqtags{trend_eqnums(i)})
end
end
else
if get_aux_variable_id(v) && M_.aux_vars(get_aux_variable_id(v)).endo_index ~= trend_variables(i)
if get_aux_variable_id(v) && M_.aux_vars(get_aux_variable_id(v)).endo_index~=trend_variables(i)
error('In a trend equation (%s) RHS variable must be lagged LHS variable!', M_.trend_component.(auxiliary_model_name).eqtags{trend_eqnums(i)})
end
end
end
% Reorder trend_eqnums_in_auxiliary_model to ensure that the order of
% the trend variables matches the order of the error correction
% variables.
[~,reorder] = ismember(M_.trend_component.toto.lhs(trend_eqnums_in_auxiliary_model), ...
M_.trend_component.toto.trend_vars(M_.trend_component.toto.trend_vars > 0));
M_.trend_component.toto.trend_vars(find(M_.trend_component.toto.trend_vars>0)));
trend_eqnums_in_auxiliary_model = trend_eqnums_in_auxiliary_model(reorder);
% Get the EC matrix (the EC term is assumend to be in t-1).
%
% TODO: Check that the EC term is the difference between the
% endogenous variable and the trend variable.
%
A0 = oo_.trend_component.(auxiliary_model_name).ec(ecm_eqnums_in_auxiliary_model,:,1);
% Get the AR matrices.
AR = oo_.trend_component.(auxiliary_model_name).ar(ecm_eqnums_in_auxiliary_model,ecm_eqnums_in_auxiliary_model,:);
% Build B matrices (VAR in levels)
B(ecm_eqnums_in_auxiliary_model, ecm_eqnums_in_auxiliary_model, 1) = eye(m) + A0 + AR(:,:,1);
B(ecm_eqnums_in_auxiliary_model, trend_eqnums_in_auxiliary_model) = -A0;
B(trend_eqnums_in_auxiliary_model, trend_eqnums_in_auxiliary_model) = eye(q);
for i = 2:p
B(ecm_eqnums_in_auxiliary_model,ecm_eqnums_in_auxiliary_model,i) = AR(:,:,i) - AR(:,:,i-1);
B(ecm_eqnums_in_auxiliary_model,ecm_eqnums_in_auxiliary_model,1) = eye(m)+A0+AR(:,:,1);
B(ecm_eqnums_in_auxiliary_model,trend_eqnums_in_auxiliary_model) = -A0;
B(trend_eqnums_in_auxiliary_model,trend_eqnums_in_auxiliary_model) = eye(q);
for i=2:p
B(ecm_eqnums_in_auxiliary_model,ecm_eqnums_in_auxiliary_model,i) = AR(:,:,i)-AR(:,:,i-1);
end
B(ecm_eqnums_in_auxiliary_model,ecm_eqnums_in_auxiliary_model,p+1) = -AR(:,:,p);
% Write Companion matrix
oo_.trend_component.(auxiliary_model_name).CompanionMatrix = zeros(size(B, 1)*size(B, 3));
for i = 1:p
for i=1:p
oo_.trend_component.(auxiliary_model_name).CompanionMatrix(1:n, (i-1)*n+(1:n)) = B(:,:,i);
oo_.trend_component.(auxiliary_model_name).CompanionMatrix(i*n+(1:n),(i-1)*n+(1:n)) = eye(n);
end

View File

@ -361,20 +361,21 @@ MODFILES = \
trend-component-and-var-models/vm1.mod \
trend-component-and-var-models/vm2.mod \
trend-component-and-var-models/vm3.mod \
trend-component-and-var-models/vm4.mod \
trend-component-and-var-models/tcm1.mod \
trend-component-and-var-models/tcm2.mod \
trend-component-and-var-models/tcm3.mod \
trend-component-and-var-models/tcm4.mod \
trend-component-and-var-models/tcm5.mod \
trend-component-and-var-models/tcm6.mod \
trend-component-and-var-models/vm1p.mod \
trend-component-and-var-models/vm2p.mod \
trend-component-and-var-models/vm3p.mod \
trend-component-and-var-models/tcm1p.mod \
trend-component-and-var-models/tcm2p.mod \
trend-component-and-var-models/tcm3p.mod \
trend-component-and-var-models/tcm4p.mod \
trend-component-and-var-models/tcm5p.mod \
trend-component-and-var-models/legacy/vm1.mod \
trend-component-and-var-models/legacy/vm2.mod \
trend-component-and-var-models/legacy/vm3.mod \
trend-component-and-var-models/legacy/tcm1.mod \
trend-component-and-var-models/legacy/tcm2.mod \
trend-component-and-var-models/legacy/tcm3.mod \
trend-component-and-var-models/legacy/tcm4.mod \
trend-component-and-var-models/legacy/tcm5.mod \
pac/var-1/example.mod \
pac/var-2/example.mod \
pac/var-3/example.mod \

View File

@ -0,0 +1,138 @@
var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112 A113 A114
A121 A122 A123 A124
A131 A132 A133 A134
A141 A142 A143 A144
A211 A212 A213 A214
A221 A222 A223 A224
A231 A232 A233 A234
A241 A242 A243 A244
A311 A312 A313 A314
A321 A322 A323 A324
A331 A332 A333 A334
A341 A342 A343 A344
B11 B12 B21 B22;
A1 = randn(4);
A2 = randn(4);
A3 = randn(4);
A1(3:4,:) = 0;
A2(3:4,:) = 0;
A3(3:4,:) = 0;
A1(1:2,3:4) = 0;
A2(1:2,3:4) = 0;
A3(1:2,3:4) = 0;
A1(3:4,3:4) = eye(2); // y3 and y4 are pure random walks.
A111 = A1(1,1);
A112 = A1(1,2);
A113 = A1(1,3);
A114 = A1(1,4);
A121 = A1(2,1);
A122 = A1(2,2);
A123 = A1(2,3);
A124 = A1(2,4);
A131 = A1(3,1);
A132 = A1(3,2);
A133 = A1(3,3);
A134 = A1(3,4);
A141 = A1(4,1);
A142 = A1(4,2);
A143 = A1(4,3);
A144 = A1(4,4);
A211 = A2(1,1);
A212 = A2(1,2);
A213 = A2(1,3);
A214 = A2(1,4);
A221 = A2(2,1);
A222 = A2(2,2);
A223 = A2(2,3);
A224 = A2(2,4);
A231 = A2(3,1);
A232 = A2(3,2);
A233 = A2(3,3);
A234 = A2(3,4);
A241 = A2(4,1);
A242 = A2(4,2);
A243 = A2(4,3);
A244 = A2(4,4);
A311 = A3(1,1);
A312 = A3(1,2);
A313 = A3(1,3);
A314 = A3(1,4);
A321 = A3(2,1);
A322 = A3(2,2);
A323 = A3(2,3);
A324 = A3(2,4);
A331 = A3(3,1);
A332 = A3(3,2);
A333 = A3(3,3);
A334 = A3(3,4);
A341 = A3(4,1);
A342 = A3(4,2);
A343 = A3(4,3);
A344 = A3(4,4);
B = rand(2);
B(1,1) = -B(1,1);
B(2,2) = -B(2,2);
B11 = B(1,1);
B12 = B(1,2);
B21 = B(2,1);
B22 = B(2,2);
trend_component_model(model_name=toto, eqtags=['eq:y1', 'eq:y2', 'eq:y3', 'eq:y4'], trends=['eq:y3', 'eq:y4']);
model;
[name='eq:y1']
diff(y1) = B11*(y1(-1)-y3(-1)) + B12*(y2(-1)-y4(-1)) +
A111*diff(y1(-1)) + A112*diff(y2(-1)) +
A211*diff(y1(-2)) + A212*diff(y2(-2)) +
A311*diff(y1(-3)) + A312*diff(y2(-3)) + e1;
[name='eq:y2']
diff(y2) = B21*(y1(-1)-y3(-1)) + B22*(y2(-1)-y4(-1)) +
A121*diff(y1(-1)) + A122*diff(y2(-1)) +
A221*diff(y1(-2)) + A222*diff(y2(-2)) +
A321*diff(y1(-3)) + A322*diff(y2(-3)) + e2;
[name='eq:y3']
y3 = y3(-1) + e3;
[name='eq:y4']
y4 = y4(-1) + e4;
end;
[EC, AR, T] = get_companion_matrix_legacy('toto');
if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
A1fake = oo_.trend_component.toto.ar(:,:,1);
A1fake(1:2,3:4) = .0;
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(oo_.trend_component.toto.ar(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(oo_.trend_component.toto.ar(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end

View File

@ -0,0 +1,135 @@
var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112 A113 A114
A121 A122 A123 A124
A131 A132 A133 A134
A141 A142 A143 A144
A211 A212 A213 A214
A221 A222 A223 A224
A231 A232 A233 A234
A241 A242 A243 A244
A311 A312 A313 A314
A321 A322 A323 A324
A331 A332 A333 A334
A341 A342 A343 A344
B11 B12 B21 B22;
A1 = randn(4);
A2 = randn(4);
A3 = randn(4);
A1(3:4,:) = 0;
A2(3:4,:) = 0;
A3(3:4,:) = 0;
A1(1:2,3:4) = 0;
A2(1:2,3:4) = 0;
A3(1:2,3:4) = 0;
A1(3:4,3:4) = eye(2); // y3 and y4 are pure random walks.
A111 = A1(1,1);
A112 = A1(1,2);
A113 = A1(1,3);
A114 = A1(1,4);
A121 = A1(2,1);
A122 = A1(2,2);
A123 = A1(2,3);
A124 = A1(2,4);
A131 = A1(3,1);
A132 = A1(3,2);
A133 = A1(3,3);
A134 = A1(3,4);
A141 = A1(4,1);
A142 = A1(4,2);
A143 = A1(4,3);
A144 = A1(4,4);
A211 = A2(1,1);
A212 = A2(1,2);
A213 = A2(1,3);
A214 = A2(1,4);
A221 = A2(2,1);
A222 = A2(2,2);
A223 = A2(2,3);
A224 = A2(2,4);
A231 = A2(3,1);
A232 = A2(3,2);
A233 = A2(3,3);
A234 = A2(3,4);
A241 = A2(4,1);
A242 = A2(4,2);
A243 = A2(4,3);
A244 = A2(4,4);
A311 = A3(1,1);
A312 = A3(1,2);
A313 = A3(1,3);
A314 = A3(1,4);
A321 = A3(2,1);
A322 = A3(2,2);
A323 = A3(2,3);
A324 = A3(2,4);
A331 = A3(3,1);
A332 = A3(3,2);
A333 = A3(3,3);
A334 = A3(3,4);
A341 = A3(4,1);
A342 = A3(4,2);
A343 = A3(4,3);
A344 = A3(4,4);
B = rand(2);
B(1,1) = -B(1,1);
B(2,2) = -B(2,2);
B11 = B(1,1);
B12 = B(1,2);
B21 = B(2,1);
B22 = B(2,2);
trend_component_model(model_name=toto, eqtags=['eq:y1', 'eq:y4', 'eq:y2', 'eq:y3'], trends=['eq:y3', 'eq:y4']);
model;
[name='eq:y1']
diff(y1) = B11*(y1(-1)-y3(-1)) + B12*(y2(-1)-y4(-1)) +
A111*diff(y1(-1)) + A112*diff(y2(-1)) +
A211*diff(y1(-2)) + A212*diff(y2(-2)) +
A311*diff(y1(-3)) + A312*diff(y2(-3)) + e1;
[name='eq:y2']
diff(y2) = B21*(y1(-1)-y3(-1)) + B22*(y2(-1)-y4(-1)) +
A121*diff(y1(-1)) + A122*diff(y2(-1)) +
A221*diff(y1(-2)) + A222*diff(y2(-2)) +
A321*diff(y1(-3)) + A322*diff(y2(-3)) + e2;
[name='eq:y3']
y3 = y3(-1) + e3;
[name='eq:y4']
y4 = y4(-1) + e4;
end;
[EC, AR, T] = get_companion_matrix_legacy('toto');
if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
if max(max(abs(AR(:,:,1)-A1(1:2,1:2))))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2(1:2,1:2))))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3(1:2,1:2))))>1e-12
error('Third order autoregressive matrix is wrong.')
end

View File

@ -0,0 +1,135 @@
var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112 A113 A114
A121 A122 A123 A124
A131 A132 A133 A134
A141 A142 A143 A144
A211 A212 A213 A214
A221 A222 A223 A224
A231 A232 A233 A234
A241 A242 A243 A244
A311 A312 A313 A314
A321 A322 A323 A324
A331 A332 A333 A334
A341 A342 A343 A344
B11 B12 B21 B22;
A1 = randn(4);
A2 = randn(4);
A3 = randn(4);
A1(3:4,:) = 0;
A2(3:4,:) = 0;
A3(3:4,:) = 0;
A1(1:2,3:4) = 0;
A2(1:2,3:4) = 0;
A3(1:2,3:4) = 0;
A1(3:4,3:4) = eye(2); // y3 and y4 are pure random walks.
A111 = A1(1,1);
A112 = A1(1,2);
A113 = A1(1,3);
A114 = A1(1,4);
A121 = A1(2,1);
A122 = A1(2,2);
A123 = A1(2,3);
A124 = A1(2,4);
A131 = A1(3,1);
A132 = A1(3,2);
A133 = A1(3,3);
A134 = A1(3,4);
A141 = A1(4,1);
A142 = A1(4,2);
A143 = A1(4,3);
A144 = A1(4,4);
A211 = A2(1,1);
A212 = A2(1,2);
A213 = A2(1,3);
A214 = A2(1,4);
A221 = A2(2,1);
A222 = A2(2,2);
A223 = A2(2,3);
A224 = A2(2,4);
A231 = A2(3,1);
A232 = A2(3,2);
A233 = A2(3,3);
A234 = A2(3,4);
A241 = A2(4,1);
A242 = A2(4,2);
A243 = A2(4,3);
A244 = A2(4,4);
A311 = A3(1,1);
A312 = A3(1,2);
A313 = A3(1,3);
A314 = A3(1,4);
A321 = A3(2,1);
A322 = A3(2,2);
A323 = A3(2,3);
A324 = A3(2,4);
A331 = A3(3,1);
A332 = A3(3,2);
A333 = A3(3,3);
A334 = A3(3,4);
A341 = A3(4,1);
A342 = A3(4,2);
A343 = A3(4,3);
A344 = A3(4,4);
B = rand(2);
B(1,1) = -B(1,1);
B(2,2) = -B(2,2);
B11 = B(1,1);
B12 = B(1,2);
B21 = B(2,1);
B22 = B(2,2);
trend_component_model(model_name=toto, eqtags=['eq:y1', 'eq:y2', 'eq:y3', 'eq:y4'], trends=['eq:y4', 'eq:y3']);
model;
[name='eq:y1']
diff(y1) = B11*(y1(-1)-y3(-1)) + B12*(y2(-1)-y4(-1)) +
A111*diff(y1(-1)) + A112*diff(y2(-1)) +
A211*diff(y1(-2)) + A212*diff(y2(-2)) +
A311*diff(y1(-3)) + A312*diff(y2(-3)) + e1;
[name='eq:y2']
diff(y2) = B21*(y1(-1)-y3(-1)) + B22*(y2(-1)-y4(-1)) +
A121*diff(y1(-1)) + A122*diff(y2(-1)) +
A221*diff(y1(-2)) + A222*diff(y2(-2)) +
A321*diff(y1(-3)) + A322*diff(y2(-3)) + e2;
[name='eq:y3']
y3 = y3(-1) + e3;
[name='eq:y4']
y4 = y4(-1) + e4;
end;
[EC, AR, T] = get_companion_matrix_legacy('toto');
if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
if max(max(abs(AR(:,:,1)-A1(1:2,1:2))))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2(1:2,1:2))))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3(1:2,1:2))))>1e-12
error('Third order autoregressive matrix is wrong.')
end

View File

@ -0,0 +1,136 @@
var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112 A113 A114
A121 A122 A123 A124
A131 A132 A133 A134
A141 A142 A143 A144
A211 A212 A213 A214
A221 A222 A223 A224
A231 A232 A233 A234
A241 A242 A243 A244
A311 A312 A313 A314
A321 A322 A323 A324
A331 A332 A333 A334
A341 A342 A343 A344
B11 B12 B21 B22;
A1 = randn(4);
A2 = randn(4);
A3 = randn(4);
A1(3:4,:) = 0;
A2(3:4,:) = 0;
A3(3:4,:) = 0;
A1(1:2,3:4) = 0;
A2(1:2,3:4) = 0;
A3(1:2,3:4) = 0;
A1(3:4,3:4) = eye(2); // y3 and y4 are pure random walks.
A111 = A1(1,1);
A112 = A1(1,2);
A113 = A1(1,3);
A114 = A1(1,4);
A121 = A1(2,1);
A122 = A1(2,2);
A123 = A1(2,3);
A124 = A1(2,4);
A131 = A1(3,1);
A132 = A1(3,2);
A133 = A1(3,3);
A134 = A1(3,4);
A141 = A1(4,1);
A142 = A1(4,2);
A143 = A1(4,3);
A144 = A1(4,4);
A211 = A2(1,1);
A212 = A2(1,2);
A213 = A2(1,3);
A214 = A2(1,4);
A221 = A2(2,1);
A222 = A2(2,2);
A223 = A2(2,3);
A224 = A2(2,4);
A231 = A2(3,1);
A232 = A2(3,2);
A233 = A2(3,3);
A234 = A2(3,4);
A241 = A2(4,1);
A242 = A2(4,2);
A243 = A2(4,3);
A244 = A2(4,4);
A311 = A3(1,1);
A312 = A3(1,2);
A313 = A3(1,3);
A314 = A3(1,4);
A321 = A3(2,1);
A322 = A3(2,2);
A323 = A3(2,3);
A324 = A3(2,4);
A331 = A3(3,1);
A332 = A3(3,2);
A333 = A3(3,3);
A334 = A3(3,4);
A341 = A3(4,1);
A342 = A3(4,2);
A343 = A3(4,3);
A344 = A3(4,4);
B = rand(2);
B(1,1) = -B(1,1);
B(2,2) = -B(2,2);
B11 = B(1,1);
B12 = B(1,2);
B21 = B(2,1);
B22 = B(2,2);
trend_component_model(model_name=toto, eqtags=['eq:y1', 'eq:y2', 'eq:y3', 'eq:y4'], trends=['eq:y3', 'eq:y4']);
model;
[name='eq:y1']
diff(y1) = B11*(y1(-1)-y3(-1)) + B12*(y2(-1)-y4(-1)) +
A111*diff(y1(-1)) + A112*diff(y2(-1)) +
A211*diff(y1(-2)) + A212*diff(y2(-2)) +
A311*diff(y1(-3)) + A312*diff(y2(-3)) + e1;
[name='eq:y4']
y4 = y4(-1) + e4;
[name='eq:y2']
diff(y2) = B21*(y1(-1)-y3(-1)) + B22*(y2(-1)-y4(-1)) +
A121*diff(y1(-1)) + A122*diff(y2(-1)) +
A221*diff(y1(-2)) + A222*diff(y2(-2)) +
A321*diff(y1(-3)) + A322*diff(y2(-3)) + e2;
[name='eq:y3']
y3 = y3(-1) + e3;
end;
[EC, AR, T] = get_companion_matrix_legacy('toto');
if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
if max(max(abs(AR(:,:,1)-A1(1:2,1:2))))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2(1:2,1:2))))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3(1:2,1:2))))>1e-12
error('Third order autoregressive matrix is wrong.')
end

View File

@ -0,0 +1,136 @@
var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112 A113 A114
A121 A122 A123 A124
A131 A132 A133 A134
A141 A142 A143 A144
A211 A212 A213 A214
A221 A222 A223 A224
A231 A232 A233 A234
A241 A242 A243 A244
A311 A312 A313 A314
A321 A322 A323 A324
A331 A332 A333 A334
A341 A342 A343 A344
B11 B12 B21 B22;
A1 = randn(4);
A2 = randn(4);
A3 = randn(4);
A1(3:4,:) = 0;
A2(3:4,:) = 0;
A3(3:4,:) = 0;
A1(1:2,3:4) = 0;
A2(1:2,3:4) = 0;
A3(1:2,3:4) = 0;
A1(3:4,3:4) = eye(2); // y3 and y4 are pure random walks.
A111 = A1(1,1);
A112 = A1(1,2);
A113 = A1(1,3);
A114 = A1(1,4);
A121 = A1(2,1);
A122 = A1(2,2);
A123 = A1(2,3);
A124 = A1(2,4);
A131 = A1(3,1);
A132 = A1(3,2);
A133 = A1(3,3);
A134 = A1(3,4);
A141 = A1(4,1);
A142 = A1(4,2);
A143 = A1(4,3);
A144 = A1(4,4);
A211 = A2(1,1);
A212 = A2(1,2);
A213 = A2(1,3);
A214 = A2(1,4);
A221 = A2(2,1);
A222 = A2(2,2);
A223 = A2(2,3);
A224 = A2(2,4);
A231 = A2(3,1);
A232 = A2(3,2);
A233 = A2(3,3);
A234 = A2(3,4);
A241 = A2(4,1);
A242 = A2(4,2);
A243 = A2(4,3);
A244 = A2(4,4);
A311 = A3(1,1);
A312 = A3(1,2);
A313 = A3(1,3);
A314 = A3(1,4);
A321 = A3(2,1);
A322 = A3(2,2);
A323 = A3(2,3);
A324 = A3(2,4);
A331 = A3(3,1);
A332 = A3(3,2);
A333 = A3(3,3);
A334 = A3(3,4);
A341 = A3(4,1);
A342 = A3(4,2);
A343 = A3(4,3);
A344 = A3(4,4);
B = rand(2);
B(1,1) = -B(1,1);
B(2,2) = -B(2,2);
B11 = B(1,1);
B12 = B(1,2);
B21 = B(2,1);
B22 = B(2,2);
trend_component_model(model_name=toto, eqtags=['eq:y4', 'eq:y1', 'eq:y2', 'eq:y3'], trends=['eq:y3', 'eq:y4']);
model;
[name='eq:y1']
diff(y1) = B11*(y1(-1)-y3(-1)) + B12*(y2(-1)-y4(-1)) +
A111*diff(y1(-1)) + A112*diff(y2(-1)) +
A211*diff(y1(-2)) + A212*diff(y2(-2)) +
A311*diff(y1(-3)) + A312*diff(y2(-3)) + e1;
[name='eq:y4']
y4 = y4(-1) + e4;
[name='eq:y2']
diff(y2) = B21*(y1(-1)-y3(-1)) + B22*(y2(-1)-y4(-1)) +
A121*diff(y1(-1)) + A122*diff(y2(-1)) +
A221*diff(y1(-2)) + A222*diff(y2(-2)) +
A321*diff(y1(-3)) + A322*diff(y2(-3)) + e2;
[name='eq:y3']
y3 = y3(-1) + e3;
end;
[EC, AR, T] = get_companion_matrix_legacy('toto');
if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
if max(max(abs(AR(:,:,1)-A1(1:2,1:2))))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2(1:2,1:2))))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3(1:2,1:2))))>1e-12
error('Third order autoregressive matrix is wrong.')
end

View File

@ -96,17 +96,17 @@ y4 = A141*y1(-1) + A142*y2(-1) + A143*y3(-1) + A144*y4(-1) +
end;
[A0, AR, B] = get_companion_matrix_preprocessor('toto');
get_companion_matrix_legacy('toto');
if max(max(abs(AR(:,:,1)-A1)))>1e-12
if max(max(abs(oo_.var.toto.ar(:,:,1)-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2)))>1e-12
if max(max(abs(oo_.var.toto.ar(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3)))>1e-12
if max(max(abs(oo_.var.toto.ar(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
@ -116,4 +116,4 @@ CompanionMatrix = [A1, A2, A3;
if max(max(abs(CompanionMatrix-oo_.var.toto.CompanionMatrix)))>1e-12
error('Companion matrix is wrong.')
end
end

View File

@ -96,17 +96,17 @@ y4 = A141*y1(-1) + A142*y2(-1) + A143*y3(-1) + A144*y4(-1) +
end;
[A0, AR, B] = get_companion_matrix_preprocessor('toto');
get_companion_matrix_legacy('toto');
if max(max(abs(AR(:,:,1)-A1)))>1e-12
if max(max(abs(oo_.var.toto.ar(:,:,1)-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2)))>1e-12
if max(max(abs(oo_.var.toto.ar(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3)))>1e-12
if max(max(abs(oo_.var.toto.ar(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
@ -116,4 +116,4 @@ CompanionMatrix = [A1, A2, A3;
if max(max(abs(CompanionMatrix-oo_.var.toto.CompanionMatrix)))>1e-12
error('Companion matrix is wrong.')
end
end

View File

@ -96,17 +96,17 @@ y1 = A111*y1(-1) + A112*y2(-1) + A113*y3(-1) + A114*y4(-1) +
end;
[A0, AR, B] = get_companion_matrix_preprocessor('toto');
get_companion_matrix_legacy('toto');
if max(max(abs(AR(:,:,1)-A1)))>1e-12
if max(max(abs(oo_.var.toto.ar(:,:,1)-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2)))>1e-12
if max(max(abs(oo_.var.toto.ar(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3)))>1e-12
if max(max(abs(oo_.var.toto.ar(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
@ -116,4 +116,4 @@ CompanionMatrix = [A1, A2, A3;
if max(max(abs(CompanionMatrix-oo_.var.toto.CompanionMatrix)))>1e-12
error('Companion matrix is wrong.')
end
end

View File

@ -2,85 +2,32 @@ var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112 A113 A114
A121 A122 A123 A124
A131 A132 A133 A134
A141 A142 A143 A144
A211 A212 A213 A214
A221 A222 A223 A224
A231 A232 A233 A234
A241 A242 A243 A244
A311 A312 A313 A314
A321 A322 A323 A324
A331 A332 A333 A334
A341 A342 A343 A344
parameters A111 A112
A121 A122
A211 A212
A221 A222
A311 A312
A321 A322
B11 B12 B21 B22;
A1 = randn(4);
A2 = randn(4);
A3 = randn(4);
A1(3:4,:) = 0;
A2(3:4,:) = 0;
A3(3:4,:) = 0;
A1(1:2,3:4) = 0;
A2(1:2,3:4) = 0;
A3(1:2,3:4) = 0;
A1(3:4,3:4) = eye(2); // y3 and y4 are pure random walks.
A1 = randn(2);
A2 = randn(2);
A3 = randn(2);
A111 = A1(1,1);
A112 = A1(1,2);
A113 = A1(1,3);
A114 = A1(1,4);
A121 = A1(2,1);
A122 = A1(2,2);
A123 = A1(2,3);
A124 = A1(2,4);
A131 = A1(3,1);
A132 = A1(3,2);
A133 = A1(3,3);
A134 = A1(3,4);
A141 = A1(4,1);
A142 = A1(4,2);
A143 = A1(4,3);
A144 = A1(4,4);
A211 = A2(1,1);
A212 = A2(1,2);
A213 = A2(1,3);
A214 = A2(1,4);
A221 = A2(2,1);
A222 = A2(2,2);
A223 = A2(2,3);
A224 = A2(2,4);
A231 = A2(3,1);
A232 = A2(3,2);
A233 = A2(3,3);
A234 = A2(3,4);
A241 = A2(4,1);
A242 = A2(4,2);
A243 = A2(4,3);
A244 = A2(4,4);
A311 = A3(1,1);
A312 = A3(1,2);
A313 = A3(1,3);
A314 = A3(1,4);
A321 = A3(2,1);
A322 = A3(2,2);
A323 = A3(2,3);
A324 = A3(2,4);
A331 = A3(3,1);
A332 = A3(3,2);
A333 = A3(3,3);
A334 = A3(3,4);
A341 = A3(4,1);
A342 = A3(4,2);
A343 = A3(4,3);
A344 = A3(4,4);
B = rand(2);
B(1,1) = -B(1,1);
@ -122,17 +69,16 @@ if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
A1fake = oo_.trend_component.toto.ar(:,:,1);
A1fake(1:2,3:4) = .0;
A1fake = AR(:,:,1);
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(oo_.trend_component.toto.ar(:,:,2)-A2)))>1e-12
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(oo_.trend_component.toto.ar(:,:,3)-A3)))>1e-12
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
end

View File

@ -1,84 +0,0 @@
var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112
A121 A122
A211 A212
A221 A222
A311 A312
A321 A322
B11 B12 B21 B22;
A1 = randn(2);
A2 = randn(2);
A3 = randn(2);
A111 = A1(1,1);
A112 = A1(1,2);
A121 = A1(2,1);
A122 = A1(2,2);
A211 = A2(1,1);
A212 = A2(1,2);
A221 = A2(2,1);
A222 = A2(2,2);
A311 = A3(1,1);
A312 = A3(1,2);
A321 = A3(2,1);
A322 = A3(2,2);
B = rand(2);
B(1,1) = -B(1,1);
B(2,2) = -B(2,2);
B11 = B(1,1);
B12 = B(1,2);
B21 = B(2,1);
B22 = B(2,2);
trend_component_model(model_name=toto, eqtags=['eq:y1', 'eq:y2', 'eq:y3', 'eq:y4'], trends=['eq:y3', 'eq:y4']);
model;
[name='eq:y1']
diff(y1) = B11*(y1(-1)-y3(-1)) + B12*(y2(-1)-y4(-1)) +
A111*diff(y1(-1)) + A112*diff(y2(-1)) +
A211*diff(y1(-2)) + A212*diff(y2(-2)) +
A311*diff(y1(-3)) + A312*diff(y2(-3)) + e1;
[name='eq:y2']
diff(y2) = B21*(y1(-1)-y3(-1)) + B22*(y2(-1)-y4(-1)) +
A121*diff(y1(-1)) + A122*diff(y2(-1)) +
A221*diff(y1(-2)) + A222*diff(y2(-2)) +
A321*diff(y1(-3)) + A322*diff(y2(-3)) + e2;
[name='eq:y3']
y3 = y3(-1) + e3;
[name='eq:y4']
y4 = y4(-1) + e4;
end;
[EC, AR, T] = get_companion_matrix_preprocessor('toto');
if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
A1fake = AR(:,:,1);
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end

View File

@ -2,85 +2,32 @@ var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112 A113 A114
A121 A122 A123 A124
A131 A132 A133 A134
A141 A142 A143 A144
A211 A212 A213 A214
A221 A222 A223 A224
A231 A232 A233 A234
A241 A242 A243 A244
A311 A312 A313 A314
A321 A322 A323 A324
A331 A332 A333 A334
A341 A342 A343 A344
parameters A111 A112
A121 A122
A211 A212
A221 A222
A311 A312
A321 A322
B11 B12 B21 B22;
A1 = randn(4);
A2 = randn(4);
A3 = randn(4);
A1(3:4,:) = 0;
A2(3:4,:) = 0;
A3(3:4,:) = 0;
A1(1:2,3:4) = 0;
A2(1:2,3:4) = 0;
A3(1:2,3:4) = 0;
A1(3:4,3:4) = eye(2); // y3 and y4 are pure random walks.
A1 = randn(2);
A2 = randn(2);
A3 = randn(2);
A111 = A1(1,1);
A112 = A1(1,2);
A113 = A1(1,3);
A114 = A1(1,4);
A121 = A1(2,1);
A122 = A1(2,2);
A123 = A1(2,3);
A124 = A1(2,4);
A131 = A1(3,1);
A132 = A1(3,2);
A133 = A1(3,3);
A134 = A1(3,4);
A141 = A1(4,1);
A142 = A1(4,2);
A143 = A1(4,3);
A144 = A1(4,4);
A211 = A2(1,1);
A212 = A2(1,2);
A213 = A2(1,3);
A214 = A2(1,4);
A221 = A2(2,1);
A222 = A2(2,2);
A223 = A2(2,3);
A224 = A2(2,4);
A231 = A2(3,1);
A232 = A2(3,2);
A233 = A2(3,3);
A234 = A2(3,4);
A241 = A2(4,1);
A242 = A2(4,2);
A243 = A2(4,3);
A244 = A2(4,4);
A311 = A3(1,1);
A312 = A3(1,2);
A313 = A3(1,3);
A314 = A3(1,4);
A321 = A3(2,1);
A322 = A3(2,2);
A323 = A3(2,3);
A324 = A3(2,4);
A331 = A3(3,1);
A332 = A3(3,2);
A333 = A3(3,3);
A334 = A3(3,4);
A341 = A3(4,1);
A342 = A3(4,2);
A343 = A3(4,3);
A344 = A3(4,4);
B = rand(2);
B(1,1) = -B(1,1);
@ -122,14 +69,16 @@ if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
if max(max(abs(AR(:,:,1)-A1(1:2,1:2))))>1e-12
A1fake = AR(:,:,1);
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2(1:2,1:2))))>1e-12
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3(1:2,1:2))))>1e-12
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
end

View File

@ -1,84 +0,0 @@
var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112
A121 A122
A211 A212
A221 A222
A311 A312
A321 A322
B11 B12 B21 B22;
A1 = randn(2);
A2 = randn(2);
A3 = randn(2);
A111 = A1(1,1);
A112 = A1(1,2);
A121 = A1(2,1);
A122 = A1(2,2);
A211 = A2(1,1);
A212 = A2(1,2);
A221 = A2(2,1);
A222 = A2(2,2);
A311 = A3(1,1);
A312 = A3(1,2);
A321 = A3(2,1);
A322 = A3(2,2);
B = rand(2);
B(1,1) = -B(1,1);
B(2,2) = -B(2,2);
B11 = B(1,1);
B12 = B(1,2);
B21 = B(2,1);
B22 = B(2,2);
trend_component_model(model_name=toto, eqtags=['eq:y1', 'eq:y4', 'eq:y2', 'eq:y3'], trends=['eq:y3', 'eq:y4']);
model;
[name='eq:y1']
diff(y1) = B11*(y1(-1)-y3(-1)) + B12*(y2(-1)-y4(-1)) +
A111*diff(y1(-1)) + A112*diff(y2(-1)) +
A211*diff(y1(-2)) + A212*diff(y2(-2)) +
A311*diff(y1(-3)) + A312*diff(y2(-3)) + e1;
[name='eq:y2']
diff(y2) = B21*(y1(-1)-y3(-1)) + B22*(y2(-1)-y4(-1)) +
A121*diff(y1(-1)) + A122*diff(y2(-1)) +
A221*diff(y1(-2)) + A222*diff(y2(-2)) +
A321*diff(y1(-3)) + A322*diff(y2(-3)) + e2;
[name='eq:y3']
y3 = y3(-1) + e3;
[name='eq:y4']
y4 = y4(-1) + e4;
end;
[EC, AR, T] = get_companion_matrix_preprocessor('toto');
if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
A1fake = AR(:,:,1);
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end

View File

@ -2,85 +2,32 @@ var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112 A113 A114
A121 A122 A123 A124
A131 A132 A133 A134
A141 A142 A143 A144
A211 A212 A213 A214
A221 A222 A223 A224
A231 A232 A233 A234
A241 A242 A243 A244
A311 A312 A313 A314
A321 A322 A323 A324
A331 A332 A333 A334
A341 A342 A343 A344
parameters A111 A112
A121 A122
A211 A212
A221 A222
A311 A312
A321 A322
B11 B12 B21 B22;
A1 = randn(4);
A2 = randn(4);
A3 = randn(4);
A1(3:4,:) = 0;
A2(3:4,:) = 0;
A3(3:4,:) = 0;
A1(1:2,3:4) = 0;
A2(1:2,3:4) = 0;
A3(1:2,3:4) = 0;
A1(3:4,3:4) = eye(2); // y3 and y4 are pure random walks.
A1 = randn(2);
A2 = randn(2);
A3 = randn(2);
A111 = A1(1,1);
A112 = A1(1,2);
A113 = A1(1,3);
A114 = A1(1,4);
A121 = A1(2,1);
A122 = A1(2,2);
A123 = A1(2,3);
A124 = A1(2,4);
A131 = A1(3,1);
A132 = A1(3,2);
A133 = A1(3,3);
A134 = A1(3,4);
A141 = A1(4,1);
A142 = A1(4,2);
A143 = A1(4,3);
A144 = A1(4,4);
A211 = A2(1,1);
A212 = A2(1,2);
A213 = A2(1,3);
A214 = A2(1,4);
A221 = A2(2,1);
A222 = A2(2,2);
A223 = A2(2,3);
A224 = A2(2,4);
A231 = A2(3,1);
A232 = A2(3,2);
A233 = A2(3,3);
A234 = A2(3,4);
A241 = A2(4,1);
A242 = A2(4,2);
A243 = A2(4,3);
A244 = A2(4,4);
A311 = A3(1,1);
A312 = A3(1,2);
A313 = A3(1,3);
A314 = A3(1,4);
A321 = A3(2,1);
A322 = A3(2,2);
A323 = A3(2,3);
A324 = A3(2,4);
A331 = A3(3,1);
A332 = A3(3,2);
A333 = A3(3,3);
A334 = A3(3,4);
A341 = A3(4,1);
A342 = A3(4,2);
A343 = A3(4,3);
A344 = A3(4,4);
B = rand(2);
B(1,1) = -B(1,1);
@ -122,14 +69,16 @@ if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
if max(max(abs(AR(:,:,1)-A1(1:2,1:2))))>1e-12
A1fake = AR(:,:,1);
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2(1:2,1:2))))>1e-12
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3(1:2,1:2))))>1e-12
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
end

View File

@ -1,84 +0,0 @@
var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112
A121 A122
A211 A212
A221 A222
A311 A312
A321 A322
B11 B12 B21 B22;
A1 = randn(2);
A2 = randn(2);
A3 = randn(2);
A111 = A1(1,1);
A112 = A1(1,2);
A121 = A1(2,1);
A122 = A1(2,2);
A211 = A2(1,1);
A212 = A2(1,2);
A221 = A2(2,1);
A222 = A2(2,2);
A311 = A3(1,1);
A312 = A3(1,2);
A321 = A3(2,1);
A322 = A3(2,2);
B = rand(2);
B(1,1) = -B(1,1);
B(2,2) = -B(2,2);
B11 = B(1,1);
B12 = B(1,2);
B21 = B(2,1);
B22 = B(2,2);
trend_component_model(model_name=toto, eqtags=['eq:y1', 'eq:y2', 'eq:y3', 'eq:y4'], trends=['eq:y4', 'eq:y3']);
model;
[name='eq:y1']
diff(y1) = B11*(y1(-1)-y3(-1)) + B12*(y2(-1)-y4(-1)) +
A111*diff(y1(-1)) + A112*diff(y2(-1)) +
A211*diff(y1(-2)) + A212*diff(y2(-2)) +
A311*diff(y1(-3)) + A312*diff(y2(-3)) + e1;
[name='eq:y2']
diff(y2) = B21*(y1(-1)-y3(-1)) + B22*(y2(-1)-y4(-1)) +
A121*diff(y1(-1)) + A122*diff(y2(-1)) +
A221*diff(y1(-2)) + A222*diff(y2(-2)) +
A321*diff(y1(-3)) + A322*diff(y2(-3)) + e2;
[name='eq:y3']
y3 = y3(-1) + e3;
[name='eq:y4']
y4 = y4(-1) + e4;
end;
[EC, AR, T] = get_companion_matrix_preprocessor('toto');
if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
A1fake = AR(:,:,1);
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end

View File

@ -2,85 +2,32 @@ var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112 A113 A114
A121 A122 A123 A124
A131 A132 A133 A134
A141 A142 A143 A144
A211 A212 A213 A214
A221 A222 A223 A224
A231 A232 A233 A234
A241 A242 A243 A244
A311 A312 A313 A314
A321 A322 A323 A324
A331 A332 A333 A334
A341 A342 A343 A344
parameters A111 A112
A121 A122
A211 A212
A221 A222
A311 A312
A321 A322
B11 B12 B21 B22;
A1 = randn(4);
A2 = randn(4);
A3 = randn(4);
A1(3:4,:) = 0;
A2(3:4,:) = 0;
A3(3:4,:) = 0;
A1(1:2,3:4) = 0;
A2(1:2,3:4) = 0;
A3(1:2,3:4) = 0;
A1(3:4,3:4) = eye(2); // y3 and y4 are pure random walks.
A1 = randn(2);
A2 = randn(2);
A3 = randn(2);
A111 = A1(1,1);
A112 = A1(1,2);
A113 = A1(1,3);
A114 = A1(1,4);
A121 = A1(2,1);
A122 = A1(2,2);
A123 = A1(2,3);
A124 = A1(2,4);
A131 = A1(3,1);
A132 = A1(3,2);
A133 = A1(3,3);
A134 = A1(3,4);
A141 = A1(4,1);
A142 = A1(4,2);
A143 = A1(4,3);
A144 = A1(4,4);
A211 = A2(1,1);
A212 = A2(1,2);
A213 = A2(1,3);
A214 = A2(1,4);
A221 = A2(2,1);
A222 = A2(2,2);
A223 = A2(2,3);
A224 = A2(2,4);
A231 = A2(3,1);
A232 = A2(3,2);
A233 = A2(3,3);
A234 = A2(3,4);
A241 = A2(4,1);
A242 = A2(4,2);
A243 = A2(4,3);
A244 = A2(4,4);
A311 = A3(1,1);
A312 = A3(1,2);
A313 = A3(1,3);
A314 = A3(1,4);
A321 = A3(2,1);
A322 = A3(2,2);
A323 = A3(2,3);
A324 = A3(2,4);
A331 = A3(3,1);
A332 = A3(3,2);
A333 = A3(3,3);
A334 = A3(3,4);
A341 = A3(4,1);
A342 = A3(4,2);
A343 = A3(4,3);
A344 = A3(4,4);
B = rand(2);
B(1,1) = -B(1,1);
@ -123,14 +70,16 @@ if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
if max(max(abs(AR(:,:,1)-A1(1:2,1:2))))>1e-12
A1fake = AR(:,:,1);
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2(1:2,1:2))))>1e-12
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3(1:2,1:2))))>1e-12
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
end

View File

@ -1,85 +0,0 @@
var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112
A121 A122
A211 A212
A221 A222
A311 A312
A321 A322
B11 B12 B21 B22;
A1 = randn(2);
A2 = randn(2);
A3 = randn(2);
A111 = A1(1,1);
A112 = A1(1,2);
A121 = A1(2,1);
A122 = A1(2,2);
A211 = A2(1,1);
A212 = A2(1,2);
A221 = A2(2,1);
A222 = A2(2,2);
A311 = A3(1,1);
A312 = A3(1,2);
A321 = A3(2,1);
A322 = A3(2,2);
B = rand(2);
B(1,1) = -B(1,1);
B(2,2) = -B(2,2);
B11 = B(1,1);
B12 = B(1,2);
B21 = B(2,1);
B22 = B(2,2);
trend_component_model(model_name=toto, eqtags=['eq:y1', 'eq:y2', 'eq:y3', 'eq:y4'], trends=['eq:y3', 'eq:y4']);
model;
[name='eq:y1']
diff(y1) = B11*(y1(-1)-y3(-1)) + B12*(y2(-1)-y4(-1)) +
A111*diff(y1(-1)) + A112*diff(y2(-1)) +
A211*diff(y1(-2)) + A212*diff(y2(-2)) +
A311*diff(y1(-3)) + A312*diff(y2(-3)) + e1;
[name='eq:y4']
y4 = y4(-1) + e4;
[name='eq:y2']
diff(y2) = B21*(y1(-1)-y3(-1)) + B22*(y2(-1)-y4(-1)) +
A121*diff(y1(-1)) + A122*diff(y2(-1)) +
A221*diff(y1(-2)) + A222*diff(y2(-2)) +
A321*diff(y1(-3)) + A322*diff(y2(-3)) + e2;
[name='eq:y3']
y3 = y3(-1) + e3;
end;
[EC, AR, T] = get_companion_matrix_preprocessor('toto');
if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
A1fake = AR(:,:,1);
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end

View File

@ -2,85 +2,32 @@ var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112 A113 A114
A121 A122 A123 A124
A131 A132 A133 A134
A141 A142 A143 A144
A211 A212 A213 A214
A221 A222 A223 A224
A231 A232 A233 A234
A241 A242 A243 A244
A311 A312 A313 A314
A321 A322 A323 A324
A331 A332 A333 A334
A341 A342 A343 A344
parameters A111 A112
A121 A122
A211 A212
A221 A222
A311 A312
A321 A322
B11 B12 B21 B22;
A1 = randn(4);
A2 = randn(4);
A3 = randn(4);
A1(3:4,:) = 0;
A2(3:4,:) = 0;
A3(3:4,:) = 0;
A1(1:2,3:4) = 0;
A2(1:2,3:4) = 0;
A3(1:2,3:4) = 0;
A1(3:4,3:4) = eye(2); // y3 and y4 are pure random walks.
A1 = randn(2);
A2 = randn(2);
A3 = randn(2);
A111 = A1(1,1);
A112 = A1(1,2);
A113 = A1(1,3);
A114 = A1(1,4);
A121 = A1(2,1);
A122 = A1(2,2);
A123 = A1(2,3);
A124 = A1(2,4);
A131 = A1(3,1);
A132 = A1(3,2);
A133 = A1(3,3);
A134 = A1(3,4);
A141 = A1(4,1);
A142 = A1(4,2);
A143 = A1(4,3);
A144 = A1(4,4);
A211 = A2(1,1);
A212 = A2(1,2);
A213 = A2(1,3);
A214 = A2(1,4);
A221 = A2(2,1);
A222 = A2(2,2);
A223 = A2(2,3);
A224 = A2(2,4);
A231 = A2(3,1);
A232 = A2(3,2);
A233 = A2(3,3);
A234 = A2(3,4);
A241 = A2(4,1);
A242 = A2(4,2);
A243 = A2(4,3);
A244 = A2(4,4);
A311 = A3(1,1);
A312 = A3(1,2);
A313 = A3(1,3);
A314 = A3(1,4);
A321 = A3(2,1);
A322 = A3(2,2);
A323 = A3(2,3);
A324 = A3(2,4);
A331 = A3(3,1);
A332 = A3(3,2);
A333 = A3(3,3);
A334 = A3(3,4);
A341 = A3(4,1);
A342 = A3(4,2);
A343 = A3(4,3);
A344 = A3(4,4);
B = rand(2);
B(1,1) = -B(1,1);
@ -123,14 +70,16 @@ if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
if max(max(abs(AR(:,:,1)-A1(1:2,1:2))))>1e-12
A1fake = AR(:,:,1);
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2(1:2,1:2))))>1e-12
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3(1:2,1:2))))>1e-12
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
end

View File

@ -1,85 +0,0 @@
var y1 y2 y3 y4;
varexo e1 e2 e3 e4;
parameters A111 A112
A121 A122
A211 A212
A221 A222
A311 A312
A321 A322
B11 B12 B21 B22;
A1 = randn(2);
A2 = randn(2);
A3 = randn(2);
A111 = A1(1,1);
A112 = A1(1,2);
A121 = A1(2,1);
A122 = A1(2,2);
A211 = A2(1,1);
A212 = A2(1,2);
A221 = A2(2,1);
A222 = A2(2,2);
A311 = A3(1,1);
A312 = A3(1,2);
A321 = A3(2,1);
A322 = A3(2,2);
B = rand(2);
B(1,1) = -B(1,1);
B(2,2) = -B(2,2);
B11 = B(1,1);
B12 = B(1,2);
B21 = B(2,1);
B22 = B(2,2);
trend_component_model(model_name=toto, eqtags=['eq:y4', 'eq:y1', 'eq:y2', 'eq:y3'], trends=['eq:y3', 'eq:y4']);
model;
[name='eq:y1']
diff(y1) = B11*(y1(-1)-y3(-1)) + B12*(y2(-1)-y4(-1)) +
A111*diff(y1(-1)) + A112*diff(y2(-1)) +
A211*diff(y1(-2)) + A212*diff(y2(-2)) +
A311*diff(y1(-3)) + A312*diff(y2(-3)) + e1;
[name='eq:y4']
y4 = y4(-1) + e4;
[name='eq:y2']
diff(y2) = B21*(y1(-1)-y3(-1)) + B22*(y2(-1)-y4(-1)) +
A121*diff(y1(-1)) + A122*diff(y2(-1)) +
A221*diff(y1(-2)) + A222*diff(y2(-2)) +
A321*diff(y1(-3)) + A322*diff(y2(-3)) + e2;
[name='eq:y3']
y3 = y3(-1) + e3;
end;
[EC, AR, T] = get_companion_matrix_preprocessor('toto');
if max(max(abs(EC-B)))>1e-12
error('Error component matrix is wrong.')
end
A1fake = AR(:,:,1);
if max(max(abs(A1fake-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end

View File

@ -96,17 +96,17 @@ y4 = A141*y1(-1) + A142*y2(-1) + A143*y3(-1) + A144*y4(-1) +
end;
get_companion_matrix('toto');
[A0, AR, B] = get_companion_matrix('toto');
if max(max(abs(oo_.var.toto.ar(:,:,1)-A1)))>1e-12
if max(max(abs(AR(:,:,1)-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(oo_.var.toto.ar(:,:,2)-A2)))>1e-12
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(oo_.var.toto.ar(:,:,3)-A3)))>1e-12
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
@ -116,4 +116,4 @@ CompanionMatrix = [A1, A2, A3;
if max(max(abs(CompanionMatrix-oo_.var.toto.CompanionMatrix)))>1e-12
error('Companion matrix is wrong.')
end
end

View File

@ -96,17 +96,17 @@ y4 = A141*y1(-1) + A142*y2(-1) + A143*y3(-1) + A144*y4(-1) +
end;
get_companion_matrix('toto');
[A0, AR, B] = get_companion_matrix('toto');
if max(max(abs(oo_.var.toto.ar(:,:,1)-A1)))>1e-12
if max(max(abs(AR(:,:,1)-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(oo_.var.toto.ar(:,:,2)-A2)))>1e-12
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(oo_.var.toto.ar(:,:,3)-A3)))>1e-12
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
@ -116,4 +116,4 @@ CompanionMatrix = [A1, A2, A3;
if max(max(abs(CompanionMatrix-oo_.var.toto.CompanionMatrix)))>1e-12
error('Companion matrix is wrong.')
end
end

View File

@ -96,17 +96,17 @@ y1 = A111*y1(-1) + A112*y2(-1) + A113*y3(-1) + A114*y4(-1) +
end;
get_companion_matrix('toto');
[A0, AR, B] = get_companion_matrix('toto');
if max(max(abs(oo_.var.toto.ar(:,:,1)-A1)))>1e-12
if max(max(abs(AR(:,:,1)-A1)))>1e-12
error('First order autoregressive matrix is wrong.')
end
if max(max(abs(oo_.var.toto.ar(:,:,2)-A2)))>1e-12
if max(max(abs(AR(:,:,2)-A2)))>1e-12
error('Second order autoregressive matrix is wrong.')
end
if max(max(abs(oo_.var.toto.ar(:,:,3)-A3)))>1e-12
if max(max(abs(AR(:,:,3)-A3)))>1e-12
error('Third order autoregressive matrix is wrong.')
end
@ -116,4 +116,4 @@ CompanionMatrix = [A1, A2, A3;
if max(max(abs(CompanionMatrix-oo_.var.toto.CompanionMatrix)))>1e-12
error('Companion matrix is wrong.')
end
end

View File

@ -0,0 +1,52 @@
// --+ options: json=compute, stochastic +--
var y x z;
varexo ex ey ez;
parameters a_y_1 a_y_2 b_y_1 b_y_2 b_x_1 b_x_2 ; // VAR parameters
parameters beta e_c_m c_z_1 c_z_2; // PAC equation parameters
a_y_1 = .2;
a_y_2 = .3;
b_y_1 = .1;
b_y_2 = .4;
b_x_1 = -.1;
b_x_2 = -.2;
beta = .9;
e_c_m = .1;
c_z_1 = .7;
c_z_2 = -.3;
var_model(model_name=toto, eqtags=['eq:x', 'eq:y']);
pac_model(auxiliary_model_name=toto, discount=beta, model_name=pacman);
model;
[name='eq:y']
y = a_y_1*y(-1) + a_y_2*diff(x(-1)) + b_y_1*y(-2) + b_y_2*diff(x(-2)) + ey ;
[name='eq:x', data_type='nonstationary']
diff(x) = b_x_1*y(-2) + b_x_2*diff(x(-1)) + ex ;
[name='eq:pac']
diff(z) = e_c_m*(x(-1)-z(-1)) + c_z_1*diff(z(-1)) + c_z_2*diff(z(-2)) + pac_expectation(pacman) + ez;
end;
shocks;
var ex = 1.0;
var ey = 1.0;
var ez = 1.0;
end;
[~, b0, ~] = get_companion_matrix_legacy('toto');
[~, b1, ~] = get_companion_matrix('toto');
if any(abs(b0(:)-b1(:))>1e-9)
error('get_companion_matrix and get_comapnion_matrix_legacy do not return the same AR matrices.').
end