摘要：The paper carries out a depth study of the crimes in the United States, considered as dependent variables, using six explanatory variables that are: Welfare, health Care, Education, Protection, Interest and Unemployment. The short and long-term relationships have been estimated by the ARDL/Bounds testing Methodology proposed by Pesaran, Shin and Smith (PSS). For each type of crimes, Violent, Property and Total crimes, a long-term equilibrium relationship has been validated and the Error Correction Model (ECM) has been built. The results show the adjustment speed towards equilibrium vary between 8.9% and 12.4%.
关键词：Spending variables; Crime rates; Descriptive analysis; Unit roots; Co-integration
