基于ARIMA模型对集采药品环孢素口服制剂的科学报量

余玺辉; 陈坚; 乔志坤; 陈静; 何敬成; 莫小兰

doi:10.13748/j.cnki.issn1007-7693.20232089

基于ARIMA模型对集采药品环孢素口服制剂的科学报量

Scientific Analysis of the Consumption of Oral Preparations of Cyclosporin Based on ARIMA Model

摘要

摘要:
目的基于时间序列的分析方法，探讨差分整合移动平均自回归模型(autoregressive integrated moving average model，ARIMA)预测集采药品环孢素口服制剂用量的可行性，为科学预测集采药品报量提供参考。
方法应用R语言和SPSS对2018年1月—2021年12月环孢素口服制剂用量的用药数据建立最优的ARIMA模型，经模型参数识别、校验后，对数据进行拟合，并验证拟合效果。
结果环孢素口服制剂用量拟合效果最佳的模型为ARIMA(0,1,1)(0,1,0)12。2022年预测值与实际值的相对误差为3.13%，证明模型拟合效果很好。
结论 ARIMA模型能够很好地拟合和预测环孢素口服制剂用量在时间序列上的变化趋势，可为集采的科学报量提供一定的参考。

Abstract:
OBJECTIVE To explore the feasibility of predicting the consumption of oral preparations of cyclosporin by autoregressive integrated moving average model(ARIMA) model based on time series analysis methods, which is provide reference for scientific prediction of drug procurement with target quantity.
METHODS R language and SPSS were used to establish the optimal ARIMA model for the data of oral preparations of cyclosporine from January 2018 to December 2021. After model parameter identification and verification, the data was fitted and the fitting effect was verified.
RESULTS ARIMA(0,1,1) (0,1,0)12 had the best fitting effect on the consumption of oral preparations of cyclosporine. The relative error between the predicted value and the actual value in 2022 was 3.13%, proving that the model had a good fitting effect.
CONCLUSION The ARIMA model can well fit and predict the trend of dosage of oral preparations of cyclosporin in time series, and can provide a certain reference for scientific analysis of the consumption of volume-based procurement policy.

HTML全文

参考文献(12)

施引文献

资源附件(0)