在台灣，機車是重要的運具之一，但由於機車的特性，駕駛人在遇到碰撞事故時往往受到的傷害比起其他車種會更加嚴重。根據世界衛生組織(World Health Organization, WHO)統計，全球每年大約有135萬人死於交通事故，並且有超過一半的交通死亡事故發生在行人、自行車騎士以及機車騎士身上。
依照國家發展委員會資料，台灣早於1993年時就以7.1%的65歲以上人口佔比成為高齡化社會，並於2018年時成為高齡社會。並且在全台灣60歲以上的高齡者持有駕照人數就有289萬人，比例接近20%，此等高比例讓高齡機車騎士的道路安全問題不可忽視。
過去關於道路安全的研究方法大多忽視了事故資料中的層級結構，而多層次模式可以處理具有階層結構的資料，探討個體層級與區域層級之間的巢套關係，以此更加完善的估計解釋因子對事故嚴重程度的影響。
本研究使用2012-2018共7年的交通事故原始資料檔，建立了多層次的二元羅吉特模式，並針對台灣20縣市的高齡機車騎士事故資料進行分析。最後分析結果發現，台灣的事故資料檔有必要以多層次模式進行分析，並且證明了兩段式左轉的重要性，未遵守兩段式左轉的高齡機車騎士較容易遇到死亡碰撞事故。另外，由人口密度、停車場密度和公共運輸市佔率通過主成份分析所得到的運輸設施發展指標也被證實會顯著影響高齡機車騎士的碰撞事故受傷嚴重程度。但與前人研究不一致的是區域層級變數中的高齡人口比例在本研究中並不會顯著影響是否死亡，證明了高齡人口比例可能並不是目前最需要急切處理的問題。

In Taiwan, motorcycle is one of the important transportation modes. However, due to the characteristics of motorcycle, riders always suffer more injuries when they encounter crash accidents than other types of vehicles. According to statistics from the World Health Organization (WHO), approximately 1.35 million people die from traffic accidents worldwide each year, and more than half of traffic fatalities occur on pedestrians, motorcycle riders, and cyclists.
Based on the National Development Council (NDC), Taiwan had become an aging society with a population of 7.1% over 65 years old as early as 1993, and it has become an aged society in 2018. It can be seen that elderly population of Taiwanese needs to be getting more seriously. And there are 2.89 million elderly citizens holding motorcycle licenses in Taiwan, accounting for 19.5% of the whole motorcycle license.
In the past, the research methods on road safety mostly ignored the hierarchical structure in the accident data, and the multilevel model can handle the data with hierarchical structure, explore the nesting relationship between the individual - level and the area-level. In this way, we can more complete the model about how explanatory factors affect the severity of the injury.
In this study, the raw data of traffic accidents for 7 years during 2012 to 2018 were used to establish a multilevel binary logistic model, and analyze the accident data of elderly motorcycle riders in 20 cities in Taiwan.
The results found that the accident data in Taiwan needed to be analyzed in a multilevel model and proved the importance of two-stage left turn. Elderly motorcycle riders who did not follow the two-stage left turn were more likely to experience fatal crash accidents. In addition, the transport development index obtained from the population density, parking density, and public transportation market share through principal component analysis have also been shown to significantly affect the severity of the crash injury of elderly motorcycle riders. However, what is inconsistent with previous studies is that the proportion of the elderly population in the area - level does not significantly affect the injury severity in this study, proving that the proportion of the elderly population may not be the most urgent issue at present.

Abdella, G. M., Kim, J., Al-Khalifa, K. N., & Hamouda, A. M. (2019). Penalized Conway-Maxwell-Poisson regression for modelling dispersed discrete data: The case study of motor vehicle crash frequency. Safety Science, 120, 157-163.
Adanu, E. K., Smith, R., Powell, L., & Jones, S. (2017). Multilevel analysis of the role of human factors in regional disparities in crash outcomes. Accident Analysis & Prevention, 109, 10-17.
Chen, S. J., Chen, C. Y., & Lin, M. R. (2018). Risk factors for crash involvement in older motorcycle riders. Accident Analysis & Prevention, 111, 109-114.
Chen, T. Y., & Jou, R. C. (2018). Estimating factors of individual and regional characteristics affecting the drink driving recidivism. Accident Analysis & Prevention, 119, 16-22.
Chen, T. Y., & Jou, R. C. (2019). Using HLM to investigate the relationship between traffic accident risk of private vehicles and public transportation. Transportation Research Part A: Policy and Practice, 119, 148-161.
Chin, H. C., & Zhou, M. (2018). A study of at-fault older drivers in light-vehicle crashes in Singapore. Accident Analysis & Prevention, 112, 50-55.
Debrabant, B., Halekoh, U., Bonat, W. H., Hansen, D. L., Hjelmborg, J., & Lauritsen, J. (2018). Identifying traffic accident black spots with Poisson-Tweedie models. Accident Analysis & Prevention, 111, 147-154.
Dupont, E., Papadimitriou, E., Martensen, H., & Yannis, G. (2013). Multilevel analysis in road safety research. Accident Analysis & Prevention, 60, 402-411.
Dupont, E., Papadimitriou, E., Martensen, H., & Yannis, G. (2013). Multilevel analysis in road safety research. Accident Analysis & Prevention, 60, 402-411.
Haddon, W. (1999). The changing approach to the epidemiology, prevention, and amelioration of trauma: the transition to approaches etiologically rather than descriptively based. Injury Prevention, 5(3), 231-235.
Haque, M. M., Chin, H. C., & Huang, H. (2009). Modeling fault among motorcyclists involved in crashes. Accident Analysis & Prevention, 41(2), 327-335.
Haque, M. M., Chin, H. C., & Huang, H. (2010). Applying Bayesian hierarchical models to examine motorcycle crashes at signalized intersections. Accident Analysis & Prevention, 42(1), 203-212.
Helai, H., Chor, C.H., Haque, M.M. (2008). Severity of driver injury and vehicle damage in traffic crashes at intersections A Bayesian hierarchical analysis. Accident Analysis and Prevention, Vol.40, pp.45–54.
Hsieh, Jun-Y. (2015). Multilevel Analysis: Theory, Method, and Application (2nd ed). Taipei: Tingmao.
Huang, H., & Abdel-Aty, M. (2010). Multilevel data and Bayesian analysis in traffic safety. Accident Analysis & Prevention, 42(6), 1556-1565.
Iannuzzi-Sucich, M., Prestwood, K. M., & Kenny, A. M. (2002). Prevalence of sarcopenia and predictors of skeletal muscle mass in healthy, older men and women. The Journals of Gerontology Series A: Biological Sciences and Medical Sciences, 57(12), M772-M777.
Jackson, T. L., & Mello, M. J. (2013). Injury patterns and severity among motorcyclists treated in US emergency departments, 2001–2008: a comparison of younger and older riders. Injury prevention, 19(5), 297-302.
Johnson, B. D. (2012). Cross-classified multilevel models: An application to the criminal case processing of indicted terrorists. Journal of Quantitative Criminology, 28(1), 163-189.
Jones, A. P., & Jørgensen, S. H. (2003). The use of multilevel models for the prediction of road accident outcomes. Accident Analysis & Prevention, 35(1), 59-69.
Jou, R. C., Yeh, T. H., & Chen, R. S. (2012). Risk factors in motorcyclist fatalities in Taiwan. Traffic injury prevention, 13(2), 155-162.
Jung, S., Xiao, Q., & Yoon, Y. (2013). Evaluation of motorcycle safety strategies using the severity of injuries. Accident Analysis & Prevention, 59, 357-364.
Kim, M., Kho, S. Y., & Kim, D. K. (2017). Hierarchical ordered model for injury severity of pedestrian crashes in South Korea. Journal of safety research, 61, 33-40.
Lenguerrand, E., Martin, J. L., & Laumon, B. (2006). Modelling the hierarchical structure of road crash data—Application to severity analysis. Accident Analysis & Prevention, 38(1), 43-53.
Lukusa, M. T., & Phoa, F. K. H. (2020). A Horvitz-type estimation on incomplete traffic accident data analyzed via a zero-inflated Poisson model. Accident Analysis & Prevention, 134, 105235.
Molnar, L. J., Charlton, J. L., Eby, D. W., Langford, J., Koppel, S., Kolenic, G. E., & Marshall, S. (2014). Factors affecting self-regulatory driving practices among older adults. Traffic injury prevention, 15(3), 262-272.
Nation Statistics (n. d.). Statistical Database. Retrieved November 23, 2019, from https://statdb.dgbas.gov.tw/pxweb/Dialog/statfile9.asp
Park, H. C., Kim, D. K., Kho, S. Y., & Park, P. Y. (2017). Cross-classified multilevel models for severity of commercial motor vehicle crashes considering heterogeneity among companies and regions. Accident Analysis & Prevention, 106, 305-314.
Rezapour, M., Moomen, M., & Ksaibati, K. (2019). Ordered logistic models of influencing factors on crash injury severity of single and multiple-vehicle downgrade crashes: A case study in Wyoming. Journal of safety research, 68, 107-118.
Road Traffic Portal Site (2015, May 29). Elderly driving safety assessment. Retrieved October 28, 2019, from https://168.motc.gov.tw/theme/elderly/post/1906121101096
Sasidharan, L., Wu, K. F., & Menendez, M. (2015). Exploring the application of latent class cluster analysis for investigating pedestrian crash injury severities in Switzerland. Accident Analysis & Prevention, 85, 219-228.
Shaheed, M. S. B., Gkritza, K., Zhang, W., & Hans, Z. (2013). A mixed logit analysis of two-vehicle crash severities involving a motorcycle. Accident Analysis & Prevention, 61, 119-128.
Stutts, J., Foss, R., & Svoboda, C. (2004). Characteristics of older motorcyclist crashes. In Annual Proceedings/Association for the Advancement of Automotive Medicine (Vol. 48, p. 197). Association for the Advancement of Automotive Medicine.
Sun, M., Sun, X., & Shan, D. (2019). Pedestrian crash analysis with latent class clustering method. Accident Analysis & Prevention, 124, 50-57.
The United Nations Economic Commission for Europe (2015). Together with UNECE on the road to safety. The United Nations Economic Commission for Europe. Geneva, Switzerland
World Health Organization (2019). World Health Statistics 2019: Monitoring health for the SDGs. World Health Organization. Department of Violence & Injury Prevention & Disability (VIP). 20 Avenue Appia. Geneva 27. Switzerland.
Wu, Q., Zhang, G., Zhu, X., Liu, X.C., Tarefder, R. (2016). Analysis of driver injury severity in single-vehicle crashes on rural and urban roadways. Accident Analysis & Prevention, 94, 35-45.
Yoon, S., Kho, S. Y., & Kim, D. K. (2017). Effect of regional characteristics on injury severity in local bus crashes: use of hierarchical ordered model. Transportation research record, 2647(1), 1-8.
Yu, S. H., Chang, K. K., Pai, C. W., Chien, W. C., Lin, D. Y., Chiu, W. T., & Lam, C. (2019). Analysis of risk factors for the severity levels of hospitalized motorcyclists in traffic accidents. Transportation Planning Journal, 48, 1-28.
Zhao, M., Liu, C., Li, W., & Sharma, A. (2018). Multivariate Poisson-lognormal model for analysis of crashes on urban signalized intersections approach. Journal of Transportation Safety & Security, 10(3), 251-265.
Zhou, M., & Chin, H. C. (2019). Factors affecting the injury severity of out-of-control single-vehicle crashes in Singapore. Accident Analysis & Prevention, 124, 104-112.