论文部分内容阅读
目的应用ARIMA模型对上海市某三级甲等妇产科专科医院分娩量的时间序列进行分析和预测。方法根据该医院2009~2013年逐月分娩量时间序列构建ARIMA模型,并根据2014年1~10月的实际分娩量对模型的预测效果进行评价。结果 ARIMA(1,1,1)(0,1,1)12模型较好地拟合了既往时间段分娩量的时间序列,模型残差为近似白噪声序列,2014年分娩量的预测值符合实际值的变动趋势。结论 ARIMA(1,1,1)(0,1,1)12模型可以较好地进行分娩量预测,为医院管理者合理安排人力、物力资源提供了科学依据。
Objective To analyze and predict the time series of delivery volume in a third-class obstetrics and gynecology hospital in Shanghai with ARIMA model. Methods The ARIMA model was constructed according to the time series of monthly deliveries from 2009 to 2013 in the hospital. The predictive effect of the model was evaluated according to the actual deliveries from January to October 2014. Results The ARIMA (1,1,1) (0,1,1) 12 model fitted the time series of birth volume in the past time well and the model residuals were approximate white noise series. The predictions of delivery volume in 2014 coincided with The actual value of the trend. Conclusion ARIMA (1,1,1) (0,1,1) 12 model can predict childbirth volume well and provide a scientific basis for hospital managers to arrange human and material resources rationally.