Table 6
Forecast accuracy of alternative Phillips curves, Germany
|
____________________________________West Germany, 1985:1 - 1998:4__________________________________ | ||||||||||
|
x = GDP |
x = unemployment rate | |||||||||
|
h |
Med |
Diff |
Mom |
WMed tr20 |
Med |
Diff |
Mom |
WMed |
tr20 | |
|
s |
s ff |
s |
s s |
s |
s ff |
s |
s |
s | ||
|
1 |
RMSFE |
0.85 |
0.85 |
0.94 |
0.94 0.97 |
0.99 |
1.00 |
1.01 |
1.05 |
1.06 |
|
DM |
-0.55 |
-0.55 |
-0.25 |
-0.21 -0.10 |
-0.05 |
-0.02 |
0.05 |
0.22 |
0.29 | |
|
MDM |
-0.54 |
-0.54 |
-0.25 |
-0.21 -0.10 |
-0.05 |
-0.02 |
0.05 |
0.22 |
0.28 | |
|
2 |
RMSFE |
0.77 |
0.70 |
0.94 |
0.98 0.95 |
0.96 |
0.89 |
1.00 |
1.01 |
1.05 |
|
DM |
-1.20 |
-1.10 |
-0.35 |
-0.11 -0.23 |
-0.20 |
-0.36 |
0.02 |
0.02 |
0.17 | |
|
MDM |
-1.13 |
-1.04 |
-0.33 |
-0.10 -0.22 |
-0.19 |
-0.34 |
0.02 |
0.02 |
0.16 | |
|
3 |
RMSFE |
0.77 |
0.70 |
0.86 |
0.85 0.82 |
0.90 |
0.88 |
0.89 |
0.90 |
0.93 |
|
DM |
-1.88** |
-1.75** |
-2.98*** |
-3.17*** -1.69** |
-0.51 |
-0.55 |
-0.83 |
-0.59 |
-0.32 | |
|
MDM |
-1.70* |
-1.58* |
-2.69*** |
-2.86*** -1.53* |
-0.46 |
-0.50 |
-0.75 |
-0.53 |
-0.29 | |
|
4 |
RMSFE |
0.52 |
0.50 |
0.85 |
0.82 0.63 |
0.98 |
0.75 |
0.78 |
0.77 |
0.84 |
|
DM |
-2.23** |
-1.78** |
-0.83 |
-1.23 -2.23** |
NA |
-1.50* |
-1.58* |
-1.79** |
-1.40* | |
|
MDM |
-1.92** |
-1.53* |
-0.71 |
-1.06 -1.92** |
0.00 |
-1.29 |
-1.36* |
-1.54* |
-1.20 | |
|
Germany, 1993:1 |
- 2007:4 | |||||||||
|
x = GDP |
x = unemployment rate | |||||||||
|
h |
Med |
Diff |
Mom |
WMed tr20 |
Med |
Diff |
Mom |
WMed |
tr20 | |
|
s |
s ff |
s |
s s |
s |
s ff |
s |
s |
s | ||
|
1 |
RMSFE |
0.95 |
1.01 |
1.18 |
1.02 1.02 |
1.06 |
1.19 |
1.24 |
1.16 |
1.09 |
|
DM |
-0.65 |
0.05 |
1.89** |
0.22 0.25 |
0.73 |
1.93** |
2.60*** |
1.63* |
0.96 | |
|
MDM |
-0.64 |
0.05 |
1.86** |
0.22 0.25 |
0.72 |
1.90** |
2.56*** |
1.61* |
0.95 | |
|
2 |
RMSFE |
0.86 |
1.05 |
1.21 |
1.01 1.01 |
1.06 |
1.16 |
1.27 |
1.26 |
1.14 |
|
DM |
-1.05 |
0.51 |
1.37* |
0.05 0.08 |
0.53 |
2.97*** |
1.87** |
3.05*** |
1.20 | |
|
MDM |
-1.00 |
0.49 |
1.31* |
0.05 0.08 |
0.51 |
2.84*** |
1.79** |
2.92*** |
1.15 | |
|
3 |
RMSFE |
0.85 |
1.04 |
1.20 |
0.96 1.00 |
1.06 |
1.21 |
1.18 |
1.22 |
1.13 |
|
DM |
-0.85 |
0.28 |
1.70** |
-0.24 0.02 |
0.34 |
1.45* |
1.28 |
1.26 |
0.74 | |
|
MDM |
-0.79 |
0.26 |
1.57* |
-0.22 0.02 |
0.31 |
1.34* |
1.19 |
1.17 |
0.69 | |
|
4 |
RMSFE |
0.84 |
0.97 |
1.23 |
0.95 1.04 |
1.12 |
1.24 |
1.28 |
1.29 |
1.18 |
|
DM |
-0.80 |
-0.15 |
2.60*** |
-0.25 0.28 |
0.63 |
1.47* |
2.39*** |
1.50* |
1.17 | |
|
MDM |
-0.72 |
-0.13 |
2.32** |
-0.22 0.25 |
0.56 |
1.31* |
2.14** |
1.34* |
1.05 | |
Notes: The Table reports the RMSFE relative to the Phillips curve benchmark model. Relative RMSFEs
smaller than 1 are documented in bold print. The lag length is set to minimize the Schwarz-information
criteria. (M)DM indicates the (modified) Diebold-Mariano test statistic. *** (**) (*) denotes significance at
the 0.99 (0.95) (0.90) level.