Lewbel (2012) heteroskedasticity-based identification
| Variables | (1) | (2) |
|---|---|---|
| LAF | LAF | |
| P_LNPEN | 0.005** (1.985) | |
| P_LNNUM | 0.077*** (3.314) | |
| Intercept | 10.380*** (54.816) | 10.414*** (58.140) |
| Control variables | Yes | Yes |
| Year and industry FE | Yes | Yes |
| N | 10,233 | 10,233 |
| Adjusted R2 | 0.793 | 0.794 |
| Diagnostic tests: | ||
| First-stage F-statistic | 34.88 | 73.616 |
| Shea’s Partial R2 | 0.256 | 0.421 |
| Kleibergen–Paap LM statistic | 530.303*** | 351.145*** |
| Variables | (1) | (2) |
|---|---|---|
| P_LNPEN | 0.005 | |
| P_LNNUM | 0.077 | |
| Intercept | 10.380 | 10.414 |
| Control variables | Yes | Yes |
| Year and industry | Yes | Yes |
| 10,233 | 10,233 | |
| Adjusted | 0.793 | 0.794 |
| Diagnostic tests: | ||
| First-stage F-statistic | 34.88 | 73.616 |
| Shea’s Partial | 0.256 | 0.421 |
| Kleibergen–Paap | 530.303 | 351.145 |
*, ** and *** indicate significance (two-tailed) at 0.10, 0.05 and 0.01 levels, respectively. Standard errors are robust to heteroscedasticity and clustered by firm. The control variables are obtained from Model 1
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.