Skip to main content

Table 6 Event-study specification: high population municipalities (Fig. 3)

From: The U-shaped crime recovery during COVID-19: evidence from national crime rates in Mexico

  All crime Assault & battery Theft & property crime Fraud Drug crime & extortion Homicides
  (1) (2) (3) (4) (5) (6)
Month − 2 − 1.444 − 0.632 − 1.378 0.184 0.348 0.034
  (1.153) (0.429) (0.842) (0.203) (0.263) (0.114)
Month 0 − 8.121*** − 2.198*** − 5.204*** − 1.113*** 0.102 0.293**
  (1.274) (0.443) (0.881) (0.195) (0.356) (0.120)
Month 1 − 32.582*** − 9.069*** − 20.273*** − 2.582*** − 0.708 0.051
  (2.068) (0.575) (1.326) (0.308) (0.539) (0.123)
Month 2 − 40.009*** − 12.552*** − 23.019*** − 2.895*** − 1.246*** − 0.297**
  (2.277) (0.649) (1.603) (0.303) (0.376) (0.118)
Month 3 − 23.737*** − 7.517*** − 13.456*** − 1.948*** − 0.706* − 0.111
  (1.847) (0.561) (1.237) (0.297) (0.427) (0.139)
Month 4 − 18.588*** − 4.923*** − 12.152*** − 0.764** − 0.785 0.036
  (1.877) (0.585) (1.282) (0.332) (0.477) (0.125)
Month 5 − 17.157*** − 5.100*** − 10.842*** − 0.437 − 0.970* 0.193
  (1.732) (0.549) (1.238) (0.314) (0.555) (0.124)
Month 6 − 9.996*** − 4.085*** − 5.468*** 0.314 − 0.675 − 0.083
  (1.888) (0.638) (1.273) (0.331) (0.485) (0.136)
Month 7 − 10.853*** − 3.584*** − 6.836*** 0.533 − 1.092* 0.126
  (2.130) (0.724) (1.366) (0.354) (0.595) (0.125)
Observations 11,670 11,670 11,670 11,670 11,670 11,670
Adjusted R-sq 0.91 0.81 0.91 0.85 0.86 0.69
Mean Dependent 87.12 20.11 53.83 4.87 5.42 2.89
Baseline FE X X X X X X
  1. Source: Mexico’s National Public Security System (Secretariado Ejecutivo del Sistema Nacional de Seguridad Pública)
  2. Plotted coefficients are event-study dummy variables, βq. Each plotted point represents the number of months before and after the lockdown. Baseline fixed effects are included at the municipality, month, and year. Vertical lines show the start and end of the lockdown. The long-dashed red line shows the month before the start of the lockdown and the short-dashed green line indicates the end of the lockdown. Robust standard errors are clustered at the municipal level. Significance levels: *p < 0.1, **p < 0.05, ***p < 0.01 Crimes are measured per 100,000 persons