1 September 2020 in Accident Analysis & Prevention
1 February 2022 in Accident Analysis & Prevention
1 August 2021 in Accident Analysis & Prevention
1 October 2017 in Accident Analysis & Prevention
1 February 2017 in Accident Analysis & Prevention
This paper evaluates the effects of the London Cycle Superhighways (CS) on cycle collisions. A total of 45 CS segments and 375 control segments are observed for a period of 8 years in London. Variables such as road characteristics, crash history and socio-economic information are included in the data set. Traffic characteristics including traffic volume, cycle volume and traffic speed are obtained from Department for Transport. We first estimate the safety effects on the CS routes using Empirical Bayes methods. Then propensity score matching methods are also applied for comparison. The introduction of cycle superhighways caused cycling traffic volumes to increase dramatically along CS routes with no significant impacts on collision rates. Our models find that the increase in traffic was associated with a rise in annual total cycle collisions of around 2.6 per km (38% in percentage). However, when we re-estimate the effects based on cycle collision rates rather than levels, our results also show that the CS routes are not more dangerous or safer than the control roads. Among the four CS routes, CS3 performs the best in protecting cyclists with a large proportion of segregated lanes whilst the cyclists have to share the lanes with motorists on other routes. It is recommended that consistent safety designs should be applied on all CS routes for a safer cycling environment.
1 August 2016 in Accident Analysis & Prevention
This paper estimates the causal effect of 20mph zones on road casualties in London. Potential confounders in the key relationship of interest are included within outcome regression and propensity score models, and the models are then combined to form a doubly robust estimator. A total of 234 treated zones and 2844 potential control zones are included in the data sample. The propensity score model is used to select a viable control group which has common support in the covariate distributions. We compare the doubly robust estimates with those obtained using three other methods: inverse probability weighting, regression adjustment, and propensity score matching. The results indicate that 20mph zones have had a significant causal impact on road casualty reduction in both absolute and proportional terms.