Exploring the Impact of Measurement Error in Police Recorded Crime Rates through Sensitivity Analysis

Abstract

It has been long known that police recorded crime data is susceptible to substantial measurement error. However, despite its limitations, police data is widely used in regression models exploring the causes and effects of crime. Furthermore, because of the complex error mechanisms affecting police data, attempts to adjust for their impact are rare and tailored to specific settings (crime types, measurement models, outcome models, and precursors or consequences of crime). Here we introduce rcme: Recounting Crime with Measurement error, a new R package to enable sensitivity assessments of the impact of measurement error in analyses using police recorded crime rates across a wide range of settings. Using two real world examples – i) the link from violent crime to disorder, and ii) the role of collective efficacy in mitigating criminal damage – we demonstrate how rcme can be used to summarise the impacts of measurement error in empirical models used in research and practice.