Bayesian Approach With the Power Prior for Road Safety Analysis

摘要: Drawing inference from current data could be more reliable if similar based on previous studies are used. We propose a full Bayesian approach with the power prior to utilize these data. The is constructed by raising likelihood function of historical where . useful informative in inference. use estimate regression coefficients and calculate accident reduction factors some covariates including median strips guardrails. also compare our method empirical Bayes method. demonstrate results several sets real were collected for two rural national roads Korea year 2002. computations executed Metropolis–Hastings algorithm which popular technique Markov chain Monte Carlo methods.