A mixed-effect statistical model for before-after speed studies

Heydari, Shahram and Miranda-Moreno, Luis F. (2013) A mixed-effect statistical model for before-after speed studies. In Annual Conference of the Canadian Society for Civil Engineering 2013: Know-How - Savoir-Faire, CSCE 2013. vol. 4, Canadian Society for Civil Engineering. pp. 3233-3242 .

Abstract

This paper proposes an efficient methodology to conduct observational before-after studies for operating speed data. The employed method has some noteworthy strengths: (i) it can analyze data at a disaggregated level to properly account for variations in the speed profile; (ii) it considers the entire distribution of speed to overcome the bias associated to the traditional approaches that represent the speed distribution with a single point estimate; (iii) it takes advantage of full Bayes methods to avoid the empirical Bayes method limitations. To illustrate the feasibility of the proposed framework, a limited sample of before-after speed dataset from Montreal was used. The effectiveness of a safety countermeasure-a reduction in speed limits-was assessed. The speed data were collected on local urban streets grouped into comparison and treatment sites. For modeling the operating speed, we employed a hierarchical mixed-effect Binomial model using a wide range of site characteristics. This model is capable of dealing with heterogeneity across observations and accounting for site specific effects. The analyses results indicated that lane width, number of lanes, and night hours affect the operating speed positively while presence of parking, peak hours, weekend, one way, and precipitation affect it negatively. Although the speed limit reduction was found to be effective in controlling the operating speed, the analyzed sample may not be representative of the entire urban areas subject to this reduction. This paper also highlights some essential issues in the data collection process and the sensitivity of the outcomes to the collection method used.

This record has no associated files available for download.

Contributors

Download statistics