ABSTRACT
Hierarchical clustering analysis framework is developed to identify benchmark and critical regions for effective road safety strategies. The regions are grouped based on agglomeration coefficient of mutually exclusive crash causation parameters. Subsequently, regions from groups with lower than a threshold index value are selected as benchmark for the poorly performing critical counterparts. Euclidean distance-based Ward's, median and centroid clustering techniques are explored through a case study of Indian states and Union Territories. As per data between 2006 and 2015, fatal crash percentages of driving under influence of drug and alcohol, excessive speeding, vehicle malfunction and road conditions related crash causation parameters, severity index and its growth rate are assessed based on respective threshold values of 6.35%, 43.28%, 2.42%, 1.79%, 26.7 and 3.1%. These are the national average of respective indices. It demonstrated the unique application of hierarchical clustering analysis in benchmark and critical region identification.
Disclosure statement
No potential conflict of interest was reported by the authors.