Poisson Regression Discontinuity Effects, Dallas Subsample
| Male | Female | |||
|---|---|---|---|---|
| Resident (1) | Visitor (2) | Resident (3) | Visitor (4) | |
| Panel A: Violent Crimes | ||||
| All | 1.045 (0.0604) | 0.947 (0.123) | 0.973 (0.0404) | 0.980 (0.100) |
| Homicide | 0.819 (0.528) | 0.110** (0.106) | 0.510 (1.461) | 0.700 (1.453) |
| Sex offenses | 6.627 (7.857) | 5.398 (8.205) | 0.912 (0.258) | 1.933* (0.767) |
| Robbery | 1.050 (0.121) | 1.083 (0.238) | 0.686** (0.122) | 0.834 (0.279) |
| Assault | 1.038 (0.0694) | 0.928 (0.148) | 0.997 (0.0436) | 0.942 (0.101) |
| Panel B: Property Crimes | ||||
| All | 1.141* (0.0818) | 1.671*** (0.237) | 1.190*** (0.0723) | 1.183 (0.148) |
| Burglary | 1.107 (0.159) | 1.420*** (0.158) | ||
| Larceny | 1.374** (0.221) | 2.352*** (0.735) | 1.257* (0.155) | 1.495* (0.317) |
| Motor vehicle theft | 1.101 (0.0964) | 1.503** (0.244) | 1.029 (0.0881) | 1.039 (0.156) |
Notes: This table contains IRR estimates for the RD effect of the MLDA on male and female victimization rates for each crime type by Dallas residency status. All regressions include second-order polynomials in age fully interacted with an indicator for age over 21 and indicator variables for the week around birthdays. Each observation is the total number of victims in each age (days) relative to the 21st birthday. Robust standard errors in parentheses. All regressions use a two-year bandwidth.
↵* p < 0.10,
↵** p < 0.05,
↵*** p < 0.01.