论文部分内容阅读
目的采用时间序列分析和预测成都市人口死亡率的动态发展趋势,建立时间序列模型,考察模型的应用效果并做出预测。方法利用时间序列自相关系数和偏相关系数识别模型,采用最小二乘法估计模型参数,用Box-Ljung统计量评价ARIMA模型的拟和度,用平均预测相对误差作为预测效果的评价指标。结果建立乘积ARIAM(0,1,1)(0,1,1)12模型,模型平均绝对百分误差MAPE=8.50%。成都市人口死亡率自2000年逐渐下降,预计序列后2年将继续呈现下降趋势。结论所运用的时间序列分析和预测模型拟合效果较好,可应用于疾病发病和死亡动态变化规律的分析和其未来发展趋势的预测、预报。
Objective To use time series analysis to predict the dynamic development trend of population mortality in Chengdu, establish a time series model, examine the application effect of the model, and make predictions. Methods The model was identified using time series autocorrelation coefficients and partial correlation coefficients. The parameters of the model were estimated by least squares method. The degree of the ARIMA model was estimated by Box-Ljung statistics, and the average prediction relative error was used as the evaluation index. Results The product ARIAM(0,1,1)(0,1,1)12 model was established, and the mean absolute percent error of the model was MAPE=8.50%. Chengdu’s population mortality rate has gradually declined since 2000, and it is expected that it will continue to show a declining trend two years after the sequence. Conclusions The time series analysis and prediction model used are well-fitted and can be applied to analyze the dynamic changes of disease incidence and death and forecast and forecast of future development trends.