Debian Codegraph @

tests/pac/var-10e/example1.mod

raw
1 // --+ options: json=compute, stochastic +--
2
3 var y x z v;
4
5 varexo ex ey ez ;
6
7 parameters a_y_1 a_y_2 b_y_1 b_y_2 b_x_1 b_x_2 d_y; // VAR parameters
8
9 parameters beta e_c_m c_z_1 c_z_2; // PAC equation parameters
10
11 a_y_1 = .2;
12 a_y_2 = .3;
13 b_y_1 = .1;
14 b_y_2 = .4;
15 b_x_1 = -.1;
16 b_x_2 = -.2;
17 d_y = .5;
18
19
20 beta = .9;
21 e_c_m = .1;
22 c_z_1 = .7;
23 c_z_2 = -.3;
24
25 var_model(model_name=toto, structural, eqtags=['eq:x', 'eq:y']);
26
27 pac_model(auxiliary_model_name=toto, discount=beta, model_name=pacman);
28
29 pac_target_info(pacman);
30 target v;
31 auxname_target_nonstationary vns;
32
33 component y;
34 growth diff(y(-1));
35 auxname pv_y_;
36 kind dd;
37
38 component x;
39 growth diff(x(-1));
40 auxname pv_dx_;
41 kind dd;
42
43 end;
44
45 model(use_dll);
46
47 [name='eq:y']
48 diff(y) = .01 + a_y_1*diff(y(-1)) + a_y_2*diff(x(-1)) + b_y_1*diff(y(-2)) + b_y_2*diff(x(-2)) + ey ;
49
50
51 [name='eq:x']
52 diff(x) = .05 + b_x_1*diff(y(-2)) + b_x_2*diff(x(-1)) + ex ;
53
54 [name='eq:v']
55 v = x + d_y*y ;
56
57 [name='zpac']
58 diff(z) = e_c_m*(pac_target_nonstationary(pacman)-z(-1)) + c_z_1*diff(z(-1)) + c_z_2*diff(z(-2)) + pac_expectation(pacman) + ez;
59
60 end;
61
62 shocks;
63 var ex = 1.0;
64 var ey = 1.0;
65 var ez = 1.0;
66 end;
67
68 // Initialize the PAC model (build the Companion VAR representation for the auxiliary model).
69 pac.initialize('pacman');
70
71 // Update the parameters of the PAC expectation model (h0 and h1 vectors).
72 pac.update.expectation('pacman');
73
74 // Set initial conditions to zero. Please use more sensible values if any...
75 initialconditions = dseries(zeros(10, M_.endo_nbr+M_.exo_nbr), 2000Q1, vertcat(M_.endo_names,M_.exo_names));
76
77 // Simulate the model for 500 periods
78 options_.solve_algo = 9;
79 TrueData = simul_backward_model(initialconditions, 500);
80
81 TrueData.save('example1.data')
82
83 // Print expanded PAC_EXPECTATION term.
84 pac.print('pacman', 'eq:pac');
85
86 clear eparams
87 eparams.e_c_m = .9;
88 eparams.c_z_1 = .5;
89 eparams.c_z_2 = .2;
90
91 // Define the dataset used for estimation
92 edata = TrueData;
93 edata.ez = dseries(NaN(TrueData.nobs, 1), 2000Q1, 'ez');
94 pac.estimate.nls('zpac', eparams, edata, 2005Q1:2005Q1+400, 'fmincon');
95
96 e_c_m_nls = M_.params(strmatch('e_c_m', M_.param_names, 'exact'));
97 c_z_1_nls = M_.params(strmatch('c_z_1', M_.param_names, 'exact'));
98 c_z_2_nls = M_.params(strmatch('c_z_2', M_.param_names, 'exact'));
99
100 save('example1.estimation.mat', 'e_c_m_nls', 'c_z_1_nls', 'c_z_2_nls')