ARIMA模型应用于月门诊量预测

Applications of ARIMA model on predictive workload of out-patient department

目的探讨季节性时间序列ARIMA预测模型在时间序列资料分析中的应用,建立门诊量的预测模型。方法采用最小二乘法估计模型参数,通过对数转换及差分方法使原始序列平稳,按照残差不相关原则、简洁原则确定模型结构,依据AIC和SBC准则确定模型阶数,建立ARIMA预测模型。结果季节自回归参数有统计学意义。方差估计值为0.001956,AIC=-443.26,SBC=-437.51。对模型进行白噪声残差分析,拟合优度统计量表中表明ARIMA的估计具体模型为:(1-B)(1-B12)Zt=(1-0.24269B)(1-0.30096B12)at是适合的。结论用所建立模型对月门诊量进行预测,结果表明ARIMA是一种短期预测精度较高的预测模型。

Objective To discuss the application of seasonal time series ARIMA predictive model and fit predictive model on workload of out-patient department. Methods Parameter of model is estimated based on conditional least squares. The structure is determined according to criteria of residual un-correlation and concision. ARIMA predictive model was fitted and the order of model was confirmed through Akaike Information Crierion and Schwarz Bayesian Criterion. Results Statistics assisted estimation of the significance of the fitted seasonal auto-regressive coefficients. The estimation of variance is 0.001956, AIC = -443.26,SBC = -437.51. Using analysis of white-noise residual of model, fit of rich table show that the best estimated ARI- MA model is （ 1 - B） （ 1 - B^12 ） Z, = （ 1 - 0. 24269B） （ 1 - 0. 30096 B^12 ） a1. Conclusion The model of ARIMA can be used to forecast for workload of out-patient department with high prediction precision of short-term time series.