论文部分内容阅读
目的 分析成都地区临床月供血量的规律,以此建立临床血液月供血量预测的时间序列ARIMA模型和乘积季节ARIMA模型,并动态进行模型的分析对比,为血液中心管理工作提供科学依据。方法 收集2006年至2016年成都市血液中心临床血液月供血量,建立ARIMA模型和乘积季节ARIMA模型,预测2016年10-12月和2017年1-3月临床血液月供血量。对备选的模型进行拟合优度的比较,筛选出最优的模型,并对模型的相对误差进行评价。结果 ARIMA(0,1,1)模型预测2016年10-12月和2017年1-3月的相对误差为1.71%、-7.45%、-3.14%、-7.66%、-15.25%、-9.74%。而ARIMA(0,1,1)×(1,1,1)~(12)模型相对误差为2.51%、-3.75%、-2.58%、-5.21%、-8.11%、-7.34%。结论 乘积季节ARIMA模型能够较好的预测短期临床供血量,持续修正的乘积季节ARIMA模型能更好的预测下一季度临床血液月供血量。
Objective To analyze the regularity of clinical monthly blood supply in Chengdu area to establish the time series ARIMA model and the product season ARIMA model for clinical blood monthly blood supply prediction and to dynamically analyze and compare the models to provide a scientific basis for the blood center management. Methods The monthly blood supply of clinical blood in Chengdu Blood Center from 2006 to 2016 was collected. ARIMA model and product season ARIMA model were established to predict the monthly blood supply of clinical blood from October to December in 2016 and January to March in 2017. The candidate models were compared for goodness of fit, the best model was screened, and the relative error of the model was evaluated. Results The ARIMA (0,1,1) model predicts the relative error of 1.71%, - 7.45%, - 3.14%, - 7.66%, - 15.25%, - 9.74% from October to December of 2016 and from January to March of 2017 respectively. . The relative errors of ARIMA (0,1,1) × (1,1,1) ~ (12) models are 2.51%, -3.75%, -2.58%, -5.21%, -8.11%, -7.34%. Conclusion The product season ARIMA model can predict the short-term clinical blood supply, and the product ARIMA model with continuous correction can better predict the blood supply of clinical blood in the next quarter.