Multiple Correspondence Analysis of Pedestrian Crashes in Rural Illinois

Abstract

During the five-year period between 2010 and 2014, there were 24,178 pedestrian crashes in Illinois. Approximately 4.39% of these pedestrian crashes occurred in rural areas; and approximately 40% of the crashes resulted in a severe injury or a fatality. Thus, pedestrian safety problems exist in rural locales, and the factors contributing to these problems need to be investigated. The goal of this study is to answer the question: “Which variable categories, when acting together, contribute more to the occurrence of pedestrian crashes in rural areas?” Crashes are random events stemming from the convergence of various factors. However, traditional statistical tools can only make pairwise comparisons of dependent and independent variables. Therefore, it is necessary to apply an analytical tool that can identify complex underlying structures in crash data and spot associations among variable categories that contribute to crash occurrence. The multiple correspondence analysis (MCA) method, which is used in this study, can do just that. According to the obtained results, categories of variables such as roadway functional class, the number of lanes, lighting conditions, weather conditions, traffic control devices, driver condition, and pedestrian condition were proved to contribute to pedestrian crashes in rural Illinois.

Statistical Analysis for Study of the Effect of Dark Clothing Color of Female Pedestrians on the Severity of Accident Using Machine Learning Methods

“…On the other hand, in a study conducted in Iran by Besharati and Tavakoli Kashani [24], low light conditions and dark clothing of pedestrians were factors that increased the likelihood of accidents, which confirms the results of this study. So, according to Baireddy et al's [25] study, wearing contrasting or reflective clothing can reduce the occurrence of accidents and make pedestrians less prone to accidents, especially at night.…”

“…ey showed that by both pedestrian dark clothing and illumination, the crashes that occurred on an urban highway were 9 times more likely to be fatal. Baireddy et al [25] assessed the factors affecting pedestrian accidents in Illinois. ey found that pedestrians not wearing contrasting clothing were involved in 66.29% of accidents.…”

Multiple Correspondence Analysis of Wrong-Way Driving Fatal Crashes on Freeways

“…For example, if two individuals choose the same category for a variable, then the distance between two individuals will be zero. If two individuals i and i ’ choose different categories k and k’ , separately, for the variable q , then the part of the squared distance between two individuals as a result of a single variable can be computed by Equation 1 ( 31 – 34 ):…”

“…Another study by Das et al ( 30 ) applied the MCA method to identify the contributing factors of fatal run-off-road crashes. Further, Baireddy et al ( 31 ) applied MCA to identify the contributing factors of pedestrian crashes in Illinois, while Jalayer et al ( 32 ) applied MCA to 15 years of WWD crash data from two states, Illinois and Alabama. According to the results obtained, four clouds of variables were identified.…”

Pattern Identification from Older Bicyclist Fatal Crashes

“…The findings of the current literature review help identify contributing factors to bicycle crashes; however, understanding the overall mechanism leading to bicyclists’ fatal or injury crash occurrence, especially for 65+ bicyclists, with a view to finding potential engineering countermeasures, requires a more extensive and innovative statistical approach. There are many traffic safety studies, especially from recent years, pertaining to the use of data mining and CA methods ( 18 – 35 ) to diagnose clusters of potential factors in complex databases. Because of the nature of the data and associated research objectives, JCA, a modified variant of CA, is a good fit for the analysis.…”