Table 6.
Random Audits and Other Real Effects
| (1) | (2) | (3) | (4) | (5) | (6) | (7) | (8) | (9) | (10) | (11) | (12) | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DV: Wages | DV: Employees | DV: Investment | DV: Receipts | |||||||||
| Post | 0.141 | -0.033 | 0.245* | -0.317 | -0.019 | -0.454 | 0.141 | 0.347 | 0.043 | 0.138 | -0.081 | 0.245* |
| (1.17) | (-0.13) | (1.86) | (-0.67) | (-0.07) | (-0.65) | (1.13) | (1.49) | (0.30) | (1.32) | (-0.56) | (1.76) | |
| Audited*Post | 0.028 | 0.009 | 0.018 | 0.359 | 0.436 | 0.322 | -0.130 | 0.091 | -0.199 | -0.218*** | -0.240* | -0.208** |
| (0.27) | (0.04) | (0.15) | (1.13) | (1.38) | (0.72) | (-1.18) | (0.44) | (-1.53) | (-2.69) | (-1.95) | (-1.99) | |
| Intercept | 6.228*** | 6.940*** | 5.893*** | 5.504*** | 4.821*** | 5.821*** | 2.534*** | 2.675*** | 2.466*** | 10.817*** | 11.871*** | 10.327*** |
| (150.10) | (79.51) | (130.81) | (39.21) | (56.32) | (28.56) | (60.03) | (33.24) | (50.32) | (299.82) | (248.71) | (216.15) | |
| Sample | Full sample | Noncompliant fums | Compliant firms | Full sample | Noncompliant fums | Compliant fans | Full sample | Noncompliant fums | Compliant firms | Full sample | Noncompliant firms | Compliant funs |
| Year Fixed Effects | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Firm Fixed Effects | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| N | 43,132 | 13,582 | 29,550 | 43,132 | 13,582 | 29,550 | 43,132 | 13,582 | 29,550 | 43,132 | 13,582 | 29,550 |
| R-Squared | 0.783 | 0.758 | 0.793 | 0.863 | 0.678 | 0.872 | 0.606 | 0.599 | 0.610 | 0.741 | 0.565 | 0.767 |
This table presents the results of our tests that examine the effects of random audits on wages, employment, investment, and receipts. The dependent variable is Wages in columns 1–3, Employees in columns 4–6, Investment in columns 7–9, and Receipts in columns 10–12. Our sample period extends from t-5 to t + 5, relative to the year that the audit begins. The dependent variables are logarithmic transformations of wages, employment, investment, and receipts, respectively. No control variables are included, as both the audit and control firms were selected randomly. Observations are weighted using the sampling weights (inverse probability of being selected) to generalize the results to the population. All variables are defined in Appendix 1. Robust t-statistics are presented below the coefficients in parentheses. ***, **, * denotes statistical significance at the 10, 5, or 1% level, respectively.