Forecasting Road Traffic Fatalities in Malaysia Using Seasonal Autoregressive Integrated Moving Average (SARIMA) Model

Sim, Ho Jen; Chong, Choo Wei; Abu Kassim, Khairil Anwar; Mooi, Ching Siew; Yuruixian, Zhang · 2022 · Crossref

DOI: 10.47836/pjst.30.2.03

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study addresses the challenge of predicting seasonal trends in road traffic fatalities in Malaysia, a critical public health issue exacerbated by increased travel during festive seasons. The research was motivated by the need to evaluate the effectiveness of the OPS Bersepadu, an integrated enforcement program launched in 2001 to reduce crashes during high-traffic periods. By developing a statistical model to forecast fatalities, the authors aimed to provide authorities with insights to optimize resource allocation and enforcement strategies. The researchers utilized monthly road traffic fatality data from the Royal Malaysian Police database spanning 1980 to 2019. The dataset was divided into pre-OPS (1980–2000) and post-OPS (2001–2019) periods to assess the program's impact. A Seasonal Autoregressive Integrated Moving Average (SARIMA) model was developed using the Box-Jenkins methodology. The process involved testing for stationarity using Augmented Dickey-Fuller and Phillips-Perron tests, identifying parameters via Autocorrelation and Partial Autocorrelation functions, and selecting the best-fit model based on Akaike and Bayesian Information Criteria. The model was validated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) for both in-sample (1980–2006) and out-of-sample (2007–2019) forecasts. The results identified SARIMA (1, 1, 2) (1, 1, 2)12 as the superior model, demonstrating the lowest error metrics across both in-sample and out-of-sample evaluations. The model effectively captured seasonal patterns, with August consistently showing the highest fatalities due to festive celebrations and school holidays. When comparing forecasted values against actual fatalities during OPS Bersepadu periods, the study found mixed outcomes. Of the 40 intervention programs analyzed, 22 resulted in actual fatalities higher than forecasted, with differences ranging from 0.4% to 24.7%. This indicates that while the enforcement program has had some success, it has not consistently reduced fatalities below predicted seasonal baselines. The significance of this study lies in its validation of SARIMA as a robust tool for forecasting monthly road traffic fatalities in Malaysia, outperforming other models like ARIMA and neural networks. The findings suggest that current enforcement strategies may require optimization to better mitigate seasonal spikes in fatalities. By providing accurate forecasts, the model enables policymakers and enforcement agencies to allocate staff, budgets, and equipment more efficiently during high-risk periods, ultimately supporting efforts to reduce the national burden of road traffic injuries and deaths.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• fatality injury trends