Applications of Subset Selection Procedures and Bayesian Ranking Methods in Analysis of Traffic Fatality Data

Abstract

Nonparametric and parametric subset selection procedures are used in the analysis of state motor vehicle traffic fatality rates (MVTFRs), for the years 1994 through 2012, to identify subsets of states that contain the ‘best’ (lowest MVTFR) and ‘worst’ (highest MVTFR) states with a prescribed probability. A new Bayesian model is developed and applied to the traffic fatality data and the results contrasted to those obtained with the subset selection procedures. All analyses are applied within the context of a two-way block design.