Table 4. Pay gap between public and private sector: Simple probit model.
β* = βpri |
Males β* = βpub |
β* = βpri |
Females β* = βpub | |
Predicted log wages ln |
Wpub = 2.2392 |
ln Wpriv = 2.0263 |
ln Wpub = 2.1516 |
ln Wpr,iv = 1.7369 |
ln wpub - ln wpri |
0.2128 ** |
0.4147 ** | ||
(Xpub - Xpri )β* |
0.2950 ** |
0.4198 ** |
0.2763 ** |
0.4732 ** |
(139.0 %) |
(197.0 %) |
(67.0 %) |
(114.0 %) | |
Xpri ( β - βpn ) |
- |
-0.9866 ** |
- |
-0.2906 |
(-463.0 %) |
- |
(-70.0 %) | ||
χPub (βPub - β*~) |
-0.8619 ** |
- |
-0.0936 | |
(-405.0 %) |
- |
(-23.0 %) |
- | |
Selection (due to differences in |
0.7797 ** |
0.2321 | ||
the selection terms) |
(366.0 %) |
(56.0 %) | ||
Sector choice |
0.7389 ** |
0.2633 ** (BC) | ||
Participation |
-0.0408 |
-0.0312 | ||
Selectivity corrected wage gap |
-0.5668 |
0.1826 |
Note: Cross-section weights applied. *,**, and *** denote significance at 10%, 5% and 1% respectively. Standard errors in parentheses, where OLS standard
errors are robust and the s.e. for the remaining models are bootstrapped. (N) refers to normal, (P) to percentile, and (BC) to bias corrected confidence
intervals (1000 replications).
314 Journal of Applied Economics