Thresholds for Employment and Unemployment - a Spatial Analysis of German Regional Labour Markets 1992-2000



15

Table 6.1: Verdoorn’s law: estimation and testing results

Non-spatial GLS estimation

Spatial SUR estimation

Output growth

Coefficient       t-statistic

0.1480         13.561

Coefficient       t-statistic

0.1906         12.434

Constant

-0.0044         -7.139

-0.0023          -4.426

D98

0.0129         13.749

0.0121         15.502

D99

0.0138         13.037

0.0126         13.128

D00

0.0143         13.510

0.0134         14.476

Empl. threshold

0.0294         7.543

0.0121          4.551

R2     SER    SSR

0.141     0.018     0.471

R2     SER     SSR

0.376     0.016     0.342

Non-spatial GLS
estimation

Spatial SUR estimation

Year

Moran's I residuals
(z values)

Moran's I residuals
(z value)

Significant eigen-
vectors

Moran's I spatial
components

1993

0.403 (8,782)

-0.046 (-0,507)

1, 2, 4

0.966

1994

0.065 (1,589)

-0.007 (0,336))

1, 2, 8

0.976

1995

0.189 (4,158)

0.043 (1,703)

1, 2, 4, 12, 18, 29

0.897

1996

0.260 (5,633)

-0.031 (0,423)

2, 3, 6, 7, 11, 16, 17,
18, 22

0.844

1997

0.152 (3,326)

-0.050 (-0,603)

1, 2, 3

0.972

1998

0.369 (7,943)

0.016 (1,647))

1, 2, 3, 4, 6, 8, 10, 12,
25, 29

0.920

1999

0.323 (6,940)

0.069 (2,660)

1, 2, 3, 5, 8, 17, 23,

27, 28, 38

0.856

2000

0.491 (10,603)

0.038 (1,936)

1, 2, 3, 4, 7, 8, 14, 15

0.959

Notes: Non-spatial GSL estimation is based on the SUR model (3.4) without applying the spatial filtering
approach. D98, D99, D00: Dummies for 1998, 1999 and 2000, R2: coefficient of determination,
SER: standard error of regression, SSR: sum of squared residuals

The high Moran coefficients of the linear combinations of the eigenvectors highlight the
common spatial characteristics across neighbouring regions in all subperiods. Accord-
ing to the qualitative classification scheme introduced by Griffith (2003, p. 107), the
MI
scatterplot trend is pronounced in six years (MI∕MImax0.9). In 1996 and 1999 the
MI/MImax values indicate a conspicuous MI scatterplot trend. Figure 6.2 shows that both
west-east and east-west trends of the spatial components dominate the map patterns



More intriguing information

1. The name is absent
2. The Making of Cultural Policy: A European Perspective
3. Distortions in a multi-level co-financing system: the case of the agri-environmental programme of Saxony-Anhalt
4. The name is absent
5. Social Balance Theory
6. The name is absent
7. The name is absent
8. The name is absent
9. The name is absent
10. From Aurora Borealis to Carpathians. Searching the Road to Regional and Rural Development