Robert J. Sampson and W. Byron Groves (1989) analyzed data from 238 British neighborhoods to test the mediating effect of indicators of social disorganization. Basing their work on that of Clifford R. Shaw and Henry D. McKay (1942), these researchers created indicators such as friendship networks, organizational participation, and the control of street-corner teenaged peer groups, and developed a theory of community level. In this article, we apply the formal logic of Sampson and Groves using data from the first Belo Horizonte victimization survey. In addition, we use data from the 2000 Brazilian Census and the Military Police. The results support the social disorganization theory and demonstrate that crime-rate differences are an effect of community level.