Measuring the relative efficiency of police precincts using data envelopment analysis

Abstract Data envelopment analysis (DEA) is used to measure the relative efficiency of the 14 police precincts in Taipei city, Taiwan. Our results indicate how DEA may be used to evaluate these police precincts from commonly available police statistical data for the years 1994–1996. To sharpen our efficiency estimates, we use window analysis, slack variable analysis, and output-oriented DEA models with both constant and variable returns to scale. The problem of the presence of non-discretionary input variables is explicitly treated in the models used. Potential improvements in technical efficiency of police precincts are examined by readjusting the particular output/input indicators. The analysis indicates that differences in operating environments, such as resident population and location factors, do not have a significant influence upon the efficiency of police precincts.