I have look at my eigenvalues with and without adjustment cost and I think the problem lies there.
This is what I get without adjustment cost (\Kappa = 0)
- Code: Select all
EIGENVALUES:
Modulus Real Imaginary
0 0 0
2.06e-18 -2.06e-18 0
7.271e-17 7.271e-17 0
0.08573 0.08573 0
0.5824 0.5824 0
0.9472 0.9472 0
0.95 0.95 0
0.95 0.95 0
0.95 0.95 0
0.979 0.979 0
1.067 1.067 0
1.075 1.074 0.04998
1.075 1.074 -0.04998
1.288 1.288 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
There are 12 eigenvalue(s) larger than 1 in modulus
for 12 forward-looking variable(s)
And this is with adjustment costs that are high enough (\Kappa >0.05):
- Code: Select all
1.056e-16 1.056e-16 0
2.268e-16 -2.268e-16 0
0.3702 0.3702 0
0.5954 0.5954 0
0.9471 0.9471 0
0.95 0.95 0
0.95 0.95 0
0.95 0.95 0
0.979 0.979 0
1.067 1.067 0
1.073 -1.073 0
1.075 1.074 0.04996
1.075 1.074 -0.04996
1.288 1.288 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
Inf Inf 0
However, I don't know exactly what to infer from this output. Thanks for your time.