Multilevel models to analyze before and after speed data

摘要: Analyzing before-after speed data is often limited to a standard comparison of various parameters. Although few studies have used model-based approach, limitations exist in terms both and methodology. The aim this paper was examine the applicability using multilevel models analyze explore effect temporal, geometrical, traffic characteristics on an urban residential context. Two models, one with homogeneous heterogeneous within-site variance, were for analyzing hourly free-flow data. study dataset collected before after posted limit (PSL) reduction from 50 km/h 40 km/h; pilot program city Edmonton, Alberta, Canada. results demonstrated appropriateness model Moreover, variance outperformed counterpart goodness-of-fit precision parameter estimates. estimations intuitive findings respect factors mean speed. In general, evaluation showed that reduced by 4.6 period, when variances used. use slightly underestimated reduction. A separate investigation revealed 5.3 4.0 local collector roads, respectively. Language: en