Safety effects of mobile speed cameras in Norfolk: No more than regression to the mean?

Abstract

This letter is a comment on the paper effects of mobile speed camera introduction on road traffic crashes and casualties in a rural county of England, published in this journal (vol. 39, issue 1, pp. 101-110, 2008). The authors of the original paper (Jones, Sauerzapf and Haynes) analyze the effects of a camera enforcement program on injury crashes in the county of Norfolk. The author of the letter has found that an error was made in the calculation of the regression-to-the-mean (RTM) effect, leading to an underestimation of RTM bias. A correction of this error would partly change the conclusions of the paper. Based on the corrected results, the study does not seem to provide evidence of an overall safety benefit due to the mobile speed camera introduction at the treated sites. The original authors respond to the letter by agreeing that the error led to an underestimation of regression to the mean bias, and that the conclusion thus needs to be amended.