Forecasting Road Traffic Deaths in Thailand: Applications of Time-Series, Curve Estimation, Multiple Linear Regression, and Path Analysis Models
Sajjakaj Jomnonkwao, Savalee Uttra, Vatanavongs Ratanavaraha
Abstract
In 2018, 19,931 people were killed in road accidents in Thailand. Thus, reduction in the number of accidents is urgently required. To provide a master plan for reducing the number of accidents, future forecast data are required. Thus, we aimed to identify the appropriate forecasting method. We considered four methods in this study: Time-series analysis, curve estimation, regression analysis, and path analysis. The data used in the analysis included death rate per 100,000 population, gross domestic product (GDP), the number of registered vehicles (motorcycles, cars, and trucks), and energy consumption of the transportation sector. The results show that the best three models, based on the mean absolute percentage error (MAPE), are the multiple linear regression model 3, time-series with exponential smoothing, and path analysis, with MAPE values of 6.4%, 8.1%, and 8.4%, respectively.