Table 5

Effect of Violence in the Probability of Migrating to the United States: IV Results 2007–2012

Dependent Variable
Homicide RateTwo-Year Homicide RateThree-Year Homicide RateCumulative Homicide Rate
(1)(2)(3)(4)
Panel A: First Stage Estimation
Municipal-0.679***-1.072***-1.152***-1.383***
(Campaign/election)(0.114)(0.143)(0.149)(0.157)
Post_Municipal-0.695***-1.036***-1.099***-1.314***
(First year in office)(0.103)(0.115)(0.121)(0.125)
Pre_Municipal-0.577***-0.914***-0.882***-1.007***
(Second year in office)(0.099)(0.122)(0.125)(0.111)
Excluded variable: Second year in office of a four year appointment
F-Statistic15.3227.2131.7436.41
Kleibergen-Paap rk LM stat43.4575.8988.3798.29
Chi-sq(2) P-val0.0000.0000.0000.000
Hansen J Statistic2.694.984.784.78
Chi-sq(2) P-val0.2610.0830.0920.092
Panel B: Second Stage Estimation
Dependent variable: Migration rate
Homicide rate0.0138***0.0085***0.0078***0.0064***
(0.004)(0.002)(0.002)(0.002)
[1.38][1.82][2.35][1.89]
Observations12,09012,09012,09012,090

Notes: The elasticity of migration with respect to the homicide rate is shown in square brackets. Standard errors are robust and clustered by municipality. Regressions include year and municipality fixed effects. *p < 0.1, **p < 0.05, ***p < 0.01.