Table 2b
Party Structure, type of governments and electoral rules
OLS and instrumental variable estimates in 1960-98 cross section
|
(1) |
(2) |
(3) |
(4) |
(5) |
(6) |
(7) |
(8) | |
|
Dep.Var |
party_frag |
nparties |
coalition |
single |
ngov |
coalition |
single |
ngov |
|
party_frag |
2.62 |
-2.63 (0.43)*** | ||||||
|
nparties |
0.24 (0.06)*** | |||||||
|
maj |
-0.09 |
-1.88 |
0.07 |
0.20 |
0.44 | |||
|
(0.05)* |
(1.48) |
(0.20) |
(0.18) |
(0.83) | ||||
|
semi |
-0.01 |
-1.29 |
0.25 |
0.02 |
0.39 | |||
|
(0.06) |
(1.81) |
(0.19) |
(0.20) |
(0.74) | ||||
|
district |
0.14 |
5.02 |
0.75 |
-0.43 |
2.22 | |||
|
(0.07)** |
(1.79)*** |
(0.20)*** |
(0.23)* |
(0.74)*** | ||||
|
threshold |
-0.01 |
-0.77 |
-0.01 |
-0.00 |
-0.16 | |||
|
(0.01) |
(0.27)*** |
(0.04) |
(0.03) |
(0.13) | ||||
|
investiture |
0.04 |
0.84 |
-0.10 |
0.35 | ||||
|
(0.19) |
(0.81) |
(0.11) |
(0.34) | |||||
|
constructive |
0.71 |
0.42 |
0.78 |
0.77 | ||||
|
(0.20)*** |
(0.51) |
(0.12)*** |
(0.48) | |||||
|
Over-id |
4.25(3) |
2.76(3) |
3.65(3) | |||||
|
Estimation |
OLS |
OLS |
OLS |
OLS |
OLS |
2SLS |
2SLS |
2SLS |
|
Adjust. R-sq. |
0.40 |
0.49 |
0.25 |
0.34 |
0.11 | |||
|
N. obs |
38 |
38 |
36 |
36 |
36 |
36 |
36 |
36 |
Robust standard errors in parentheses; * significant at 10%; ** significant at 5%; *** significant at 1%
Controls included in all OLS specification, cols (1)-(5): lpop, col_uka
Second-stage variables in 2SLS regressions, cols (6)-(8): lpop, col_uka, investiture, constructive
First-stage variables in the 2SLS specifications: maj, semi, district, threshold, and all second-stage variables
Over-id is Hansen’s J statistic for test of the over-identifying restriction implied by the electoral rule variables having no direct effect on the type of government;
critical values at 5% significance are 7.81 in all columns