论文部分内容阅读
[目的]探讨季节性差分自回归滑动平均(SARIMA)模型预测道路交通伤害的可行性,为掌握上海市交通伤害趋势提供依据。[方法]利用EVIEWS软件对2000—2009年上海市道路交通伤害死亡的季度数据进行SARIMA模型拟合,并利用2010年数据对预测数据进行验证。[结果]上海市道路交通死亡具有明显的季节要素,趋势要素呈逐步下降趋势;对原始图形识别后,综合考察几种模型拟合优劣,最终采用SARIMA(2,1,0)(0,1,1)4,其能很好地拟合上海市道路交通伤害死亡情况。2010年4个季度死亡率预测值分别为1.49/105、1.74/105、1.93/105和2.06/105,实际值均在预测区间内,残差也显示为白噪声序列。预测结果较好。[结论]SARIMA模型是一种能较好地预测道路交通伤害趋势的工具,可为预防与控制道路交通伤害提供决策依据。
[Objective] The research aimed to discuss the feasibility of seasonal differential autoregressive moving average (SARIMA) model in predicting road traffic injuries and provide the basis for grasping the traffic injury trend in Shanghai. [Methods] The SARIMA model was fitted to the quarterly data of road traffic injuries in Shanghai from 2000 to 2009 using EVIEWS software. The data of 2010 were used to verify the forecasting data. [Results] The road traffic deaths in Shanghai had obvious seasonal elements, and the trend elements showed a gradual downward trend. After the original graphics were identified, several models were fitted to each other. Finally, SARIMA (2,1,0) (0, 1,1) 4, which can well fit the death toll of road traffic injuries in Shanghai. The four-quarter mortality forecast in 2010 was 1.49 / 105, 1.74 / 105, 1.93 / 105 and 2.06 / 105 respectively. The actual values were within the prediction range and the residuals also showed as white noise. The forecast result is better. [Conclusion] The SARIMA model is a tool that can better predict the trend of road traffic injuries, and can provide decision-making basis for preventing and controlling road traffic injuries.