Table 1: Estimation Results
|
Parameter |
Time-varying Model |
Constant Model | ||
|
Estimate |
Standard Error |
Estimate |
Standard Error | |
|
y |
-0.11 |
0.76 |
-0.31 |
0.47 |
|
r |
2.99 |
0.74 |
2.79 |
0.46 |
|
θ |
0.71 |
0.28 |
0.72 |
0.19 |
|
γy |
0.35 |
0.13 |
0.14 |
0.03 |
|
γπ |
0.53 |
0.25 |
0.16 |
0.05 |
|
ρ |
0.62 |
0.10 |
0.91 |
0.03 |
|
πr |
4.00 |
0.73 | ||
|
δ |
0.08 |
0.04 | ||
|
η |
-0.35 |
0.26 | ||
|
cDS |
-0.01 |
0.16 |
0.07 | |
|
cDr |
0.13 | |||
|
cSr |
0.21 | |||
|
cDτ |
0.19 |
0.10 |
0.18 | |
|
cSτ |
0.14 |
0.06 |
0.17 | |
|
crτ |
0.29 |
0.08 |
0.25 | |
|
cST |
0.77 |
0.34 | ||
|
σD |
0.68 |
0.05 |
0.67 | |
|
σS |
0.71 |
0.06 |
0.76 | |
|
σr |
0.76 |
0.07 |
0.93 | |
|
στ |
0.34 |
0.03 |
0.36 | |
|
σT = σP |
0.21 |
0.13 | ||
The time-varying model was estimated using maximum likelihood with Kalman filtering
techniques to estimate the two unobserved state variables (the inflation target and the
perceived inflation target). The constant model was estimated using a generalized version
of the seemingly unrelated regression method that allows for cross-equation restrictions
on parameters. Estimates of the coefficients that summarize the structural relationships
between the residuals and estimates of the standard errors of the structural shocks are
obtained using a Cholesky decomposition of the estimated residual covariance matrix.
Estimates of the VAR slope coefficients in β(L) are provided in Table 2 for the time-varying
model and in Table 3 for the constant model.
33