各位大神,小弟做了一个svar模型。最后结果出来这样: Structural VAR is over-identified (5 degrees of freedom)
Model: Ae = Bu where E[uu']=I
Restriction Type: long-run pattern matrix
Long-run response pattern:
1 0 0 0 0
C(1) 1 0 0 0
C(2) 0 1 C(9) 0
C(3) C(5) C(7) 1 0
C(4) C(6) C(8) C(10) 1
Coefficient Std. Error z-Statistic Prob.
C(1) -0.051254 0.131306 -0.390342 0.6963
C(2) 0.897000 0.424027 2.115429 0.0344
C(3) -0.152595 0.166916 -0.914198 0.3606
C(4) -0.045048 0.139614 -0.322659 0.7470
C(5) 0.756224 0.014453 52.32435 0.0000
C(6) 0.292286 0.131407 2.224291 0.0261
C(7) -0.209915 0.010725 -19.57279 0.0000
C(8) -0.027504 0.131362 -0.209375 0.8342
C(9) -3.070563 0.045815 -67.02137 0.0000
C(10) 0.210588 0.131324 1.603576 0.1088
Log likelihood 256.9338
LR test for over-identification:
Chi-square(5) 962.5843 Probability 0.0000
Estimated A matrix:
1.000000 0.000000 0.000000 0.000000 0.000000
0.000000 1.000000 0.000000 0.000000 0.000000
0.000000 0.000000 1.000000 0.000000 0.000000
0.000000 0.000000 0.000000 1.000000 0.000000
0.000000 0.000000 0.000000 0.000000 1.000000
Estimated B matrix:
0.009951 0.255493 -0.061403 0.322731 0.046098
0.003838 0.461548 -0.077476 0.285368 0.520846
0.000118 0.589768 0.093270 0.442703 -8.384784
-0.000660 0.046583 -0.010675 0.054473 0.061095
4.49E-05 -0.069519 0.020276 -0.085682 0.225551
请问一下,这模型成功了吗?
跪谢!