Time Series Analysis of the Traffic Accident─Externality of Large Automobiles

• Main Authors: Chun-Chiang Lin, 林鈞鏘
• Other Authors: 曾郁仁
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/25337840659429875464

碩士 === 國立臺灣大學 === 財務金融學研究所 === 101 === The objective of this paper is to verify the hypothesis that increasing large automobiles cause the accident externality. This paper is done by time series analysis with aggregate time series data from Jan. 2001 to Dec. 2012 in Taiwan. Dependent variables are numbers of traffic accidents and number of injured passengers and fatalities which are examined in different models separately. Independent variables include gasoline consumption that was examined in Garcia-Ferrer and Hoyo(1987) and three different ratio of large automobiles examined in different models. A large automobile is defined to be an automobile with engine displacement more than 1800CC. The externality is measured by three different large automobiles ratios which are the ratio of large automobiles in all automobiles, the ratio of large automobiles in all passenger sedans and pickup trucks, the ratio of large automobiles in all passenger cars. The empirical result shows that the large automobile ratios significantly increase numbers of traffic accidents but less significantly increases number of injured passengers and fatalities. Among the three ratios, the ratio of large automobiles in all automobiles is more significant than the others.