Quantifying the causal effect of speed cameras on road traffic accidents via an approximate Bayesian doubly robust estimator
- Published: D. J. Graham, et al, 2017
- Authors: D. J. Graham, et al
- Date Added: 19 May 2017
- Last Update: 19 May 2017
The paper develops an approximate Bayesian doubly-robust (DR) estimation method to quantify the causal effect of speed cameras on road traffic accidents.
A causal DR approach combines propensity score (PS) and outcome regression (OR) models to give an average treatment effect (ATE) estimator that is consistent and asymptotically normal under correct specification of either of the two component models. The approach is developed within a novel approximate Bayesian framework to derive posterior predictive distributions for the ATE of speed cameras on road traffic accidents.
The results for England indicate significant reductions in the number of accidents at speed cameras sites (mean ATE = -30%)
The proposed method offers a promising approach for evaluation of transport safety interventions.
Doubly robust; Bayesian inference; propensity score; average treatment effect; speed cameras; casualties.