Table A3: IV-Estimates (Second stage)
Dependent variable: |
Log number of long-term unemployed finding a job each month | |||
(1) |
(2) |
(3) |
(4) | |
Approved Local Provider |
-0.167 |
-0.204* |
-0.277* |
-0.297* |
[0.092] |
[0.090] |
[0.121] |
[0.129] | |
Specialized case management |
-0.078* |
-0.077** |
-0.080** | |
[0.027] |
[0.026] |
[0.026] | ||
Own vacancy recruitment service |
0.093 |
0.100 | ||
[0.049] |
[0.055] | |||
Integrated matching approach |
0.021 |
0.024 | ||
[0.036] |
[0.036] | |||
Length of first interview (Log) |
0.018 | |||
[0.024] | ||||
First interview within 2 weeks |
0.004 | |||
[0.034] | ||||
Agreement signed |
0.043 | |||
[0.057] | ||||
Long-term unemployed (Log) |
0.703** |
0.685** |
0.681** |
0.681** |
[0.047] |
[0.044] |
[0.035] |
[0.034] | |
Long-term unemployed in neighbouring |
-0.022 |
0.005 |
0.021 |
0.023 |
[0.061] |
[0.060] |
[0.053] |
[0.053] | |
Short-term unemployed (Log) |
0.227 |
0.258* |
0.239* |
0.246* |
[0.111] |
[0.106] |
[0.106] |
[0.104] | |
Short-term unemployed in neighbouring |
-0.194 |
-0.214 |
-0.245* |
-0.250* |
[0.103] |
[0.102] |
[0.093] |
[0.092] | |
New vacancies (Log) |
-0.024 |
-0.012 |
-0.005 |
-0.011 |
[0.047] |
[0.039] |
[0.037] |
[0.037] | |
New vacancies in neighbouring regions |
0.115* |
0.101* |
0.110* |
0.112* |
[0.040] |
[0.039] |
[0.039] |
[0.040] | |
Rural regions |
0.019 |
0.023 |
0.042 |
0.039 |
[0.036] |
[0.036] |
[0.038] |
[0.040] | |
Metropolitan regions |
-0.120* |
-0.116* |
-0.103* |
-0.107* |
[0.048] |
[0.040] |
[0.039] |
[0.042] | |
East Germany |
-0.014 |
-0.007 |
0.013 |
0.007 |
[0.049] |
[0.045] |
[0.045] |
[0.045] | |
Population (Log) |
0.156 |
0.137 |
0.134 |
0.131 |
[0.094] |
[0.084] |
[0.082] |
[0.085] | |
Constant |
-2.977** |
-2.844** |
-2.630** |
-2.708** |
[0.637] |
[0.597] |
[0.528] |
[0.504] | |
Observations |
409 |
399 |
399 |
387 |
F-Statistic |
25.87 |
24.00 |
26.47 |
29.74 |
Durbin-Wu-Hausman Test (p-value) |
0.174 |
0.149 |
0.130 |
0.095 |
R-squared |
0.98 |
0.98 |
0.98 |
0.98 |
Standard errors are given in parentheses. Coefficients with * and ** indicate significance at a 5 % and 1 %
level, respectively. Observations are clustered at the level of the 16 German states and weighted accordingly.
22