Detecting Corporate Crime: An Estimate for Hidden Offending

• In Event: Euroc - Detecting and reacting to Corporate Crime

Abstract

Quantitative corporate crime research is generally based on registration data. Such data is collected by regulatory agencies as part of their obligation to monitor compliance and register offending behaviour. However, the data may suffer from detection bias. That is, not all offending can be detected through current regulatory practices.
In contrast to mainstream criminological research, we cannot apply victim surveys or self-report studies to estimate the true figure of offending. To overcome this problem, we examine the application of a detection controlled estimation model to estimate the extent of undetected corporate offending. We first assess the performance of the model using a simulated dataset. Next, we apply the model to a dataset of offending in Dutch inland shipping.
Finally, benefits and disadvantages of the model as well as possible applications in other contexts are discussed.

Authors

• Jelmar Meester, VU Amsterdam

• Sally S Simpson, University of Maryland

• Robert Brame, University of Maryland