Open AccessForecasting Road Traffic Fatalities in Malaysia Using Seasonal Autoregressive Integrated Moving Average (SARIMA) Model
Author(s) -
Ho Jen Sim,
Choo Wei Chong,
Khairil Anwar Abu Kassim,
Ching Siew Mooi,
Yuruixian Zhang
Publication year - 2022
Publication title -
pertanika journal of science and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.174
H-Index - 15
eISSN - 2231-8526
pISSN - 0128-7680
DOI - 10.47836/pjst.30.2.03
Subject(s) - autoregressive integrated moving average , transport engineering , enforcement , road traffic , traffic volume , seasonality , geography , engineering , statistics , time series , mathematics , political science , law
In Malaysia, travel activities become more intense during the festive seasons, whereby traffic volume on the roads on average increases about 30%. Consequently, this inevitably increases road traffic fatalities. An integrated enforcement program called the OPS Bersepadu has been carried out since 2011 to ensure high road safety performance. This study was carried out to develop a statistical model for predicting the seasonality of traffic fatalities. A Seasonal Autoregressive Integrated Moving Average (SARIMA) model was used to fit road fatalities data between 1980 and 2000 and forecast traffic fatalities from 2001 to 2019. The results showed that the SARIMA (1, 1, 2) (1, 1, 2)12 model fitted the data fairly well and suggest that the SARIMA model is a possible tool that provides an overview of the seasonal patterns of traffic fatalities in Malaysia. The forecasted traffic fatalities based on the SARIMA model were then compared with the actual traffic fatalities during the festive months to explore the effectiveness of the OPS Bersepadu programme to help enforcement authorities allocate optimal resources that could increase the efficiency of enforcement activities to reduce road traffic fatalities.