Statistical Footprints of Corruption: ‘Vanity Fair’ of Automobile License Plates in Russia

Abstract

We offer a novel big data approach to corruption detection and measurement by using statistical anomalies in publicly observable allocations which corruption affects in a predictable manner. While each individual incidence of corruption remains undetectable under the veil of secrecy, systemic corruption changes distributions of observable outcomes, and thus leaves measurable statistical footprints. We apply this approach to measuring corruption in Russian traffic police, which issues auto- mobile license plates. Some of such plates serve as signs of status and prestige, and they are heavily concentrated among more expensive and especially luxury classes and brands, whereas if the official rules were followed, the distributions should have been close to uniform. Such discrepancies provide evidence-based measures of corruption in traffic police, which exhibit significant correlation with road accidents, injuries and fatalities.

Keywords: Corruption, Police, Law Enforcement, Administrative data, Forensic Economics

JEL Classification: K13, K42, O17, P37