Table 5.
Average partial effects of Mundlak/Chamberlain panel probit regressions about restrictions in hiring new workers (dependent variable = 1 if firm reports restrictions)
| (a) Firm reports restrictions in hiring new workers | (b) firm reports restrictions in hiring new skilled workers | |
|---|---|---|
| Lagged hiring restrictions |
−0.043** (0.004) |
−0.046** (0.003) |
| Log. of running sum of expansion investments |
0.004** (0.001) |
0.003** (0.001) |
| Collective bargaining agreement |
−0.002 (0.007) |
−0.004 (0.006) |
| Log. of valued added |
0.007* (0.004) |
0.006‡ (0.003) |
| Share of workers with a degree from university |
0.021 (0.018) |
0.007 (0.017) |
| Share of female workers |
0.023 (0.017) |
0.035* (0.015) |
| Share of temporary employed |
0.052** (0.019) |
0.058** (0.018) |
| Share of workers subject to the German social security system |
−0.086** (0.016) |
−0.081** (0.015) |
| Share of apprentices |
−0.055‡ (0.032) |
−0.024 (0.030) |
| Share of EU foreign workers |
−0.043 (0.028) |
−0.016 (0.025) |
| Share of non-EU foreign workers |
0.000 (0.029) |
−0.019 (0.026) |
| Share of workers older than 50 |
0.053** (0.013) |
0.044** (0.013) |
| Share of workers younger than 25 |
0.010 (0.019) |
0.013 (0.017) |
| Exporting firm |
0.001 (0.008) |
0.001 (0.007) |
| Foreign ownership |
0.005 (0.014) |
−0.005 (0.014) |
| Individually owned or partnership |
0.004 (0.016) |
0.007 (0.015) |
| Single establishment |
−0.002 (0.009) |
−0.002 (0.008) |
| High competition |
−0.010** (0.004) |
−0.010** (0.004) |
| Western Germany |
−0.005* (0.002) |
−0.003 (0.002) |
| Profitability (ref.: low profitability) | ||
| high |
0.020** (0.005) |
0.026** (0.005) |
| average |
0.007 (0.004) |
0.012** (0.004) |
| Log. pseudolikelihood | −18,478.229 | −16,202.855 |
| Pseudo-R2 | 0.4099 | 0.4228 |
| Wald-Test χ2(df.) |
23,426.93** (403) |
20,504.18** (403) |
| Observations (Establishments) |
62,879 (17,297) |
62,879 (17,297) |
Source: IAB Establishment Panel 2008–2018.
Note: The model also includes the following dichotomous and auxiliary variables: family management (two dummies) and state of machinery (two dummies), nine time dummies, establishment size (six dummies), 42 industry dummies. The Chamberlain/Mundlak approach for unbalanced panels requires including the means of the time-varying covariates and an indicator that identifies the number of observations of each unit respectively the interactions of both in the regression (Wooldridge 2019). Standard errors are adjusted for clustering on establishments. **; * and ‡ denote significance at the .01; .05 and .10 level, respectively