Search

Bicycles are an eco-friendly mode of transportation, and in the capital city of South Korea, Seoul, efforts are being made to encourage citizens to use bicycles. However, without appropriate safety measures, these efforts can lead to an increase in bicycle-related traffic accidents. To promote bicycle usage while ensuring safety, this study identified various factors that influence bicycle accidents. Data were utilized that had not been properly considered in previous bicycle accident-related studies, including slope and the level of public transportation services. By considering the factors influencing bicycle traffic accidents, various models were constructed, and through comparisons of statistical indicators, the optimal model was selected geographically weighted negative binomial regression. Ultimately, three significant conclusions to ensure bicycle safety were drawn. First, across all areas of Seoul, an increase in road slope leads to a decrease in bicycle-related accidents. Furthermore, for certain Traffic Analysis Zones (TAZs), as the number of local buses (or neighborhood/community buses) increases, the bicycle traffic volume decreases, resulting in a reduction in bicycle accidents. Lastly, for some TAZs, an increase in bicycle lanes to be installed into the roadway was associated with an increase in bicycle accidents. [ABSTRACT FROM AUTHOR]

Abstract: We consider zero-inflated Poisson and zero-inflated negative binomial regression models to analyze discrete count data containing a considerable amount of zero observations. Analysis of current data could be empirically feasible if we utilize similar data based on previous studies. proposed the power prior to incorporate certain information from the historical data available from previous studies. The power prior is constructed by raising the likelihood function of the historical data to the power where . The power prior is a useful informative prior in Bayesian inference. We estimate regression coefficients associated with several safety countermeasures. We use Markov chain and Monte Carlo techniques to execute some computations. The empirical results show that the zero-inflated models with the power prior perform better than the frequentist approach. [Copyright &y& Elsevier]