在线咨询
中国工业与应用数学学会会刊
主管：中华人民共和国教育部
主办：西安交通大学
ISSN 1005-3085  CN 61-1269/O1
工程数学学报

工程数学学报 ›› 2025, Vol. 42 ›› Issue (5): 983-990.doi: 10.3969/j.issn.1005-3085.2025.05.014cstr: 32411.14.cjem.CN61-1269/O1.2025.05.014

• • 上一篇    

基于变点模型的COVID-19全国无症状感染人数特征研究

孙治国1,  金 浩1,2,  苏梦琳1   

  1. 1. 西安科技大学理学院，西安 710600

    2. 西安科技大学计算机科学与技术学院，西安 710600

  • 收稿日期:2023-03-08 接受日期:2023-09-18 出版日期:2025-10-15 发布日期:2025-12-15
  • 通讯作者: 金浩 E-mail: jinhao_2004@126.com
  • 基金资助:
    国家自然科学基金 (71473194)；陕西省科技厅自然科学基金 (2020JM513).

The Study on Characteristics of Asymptomatic Patients of COVID-19 in China Based on Change-point Models

SUN Zhiguo1,  JIN Hao1,2,  SU Menglin1   

  1. 1. School of Science, Xi'an University of Science and Technology, Xi'an 710600

    2. School of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an 710600

  • Received:2023-03-08 Accepted:2023-09-18 Online:2025-10-15 Published:2025-12-15
  • Contact: H. Jin. E-mail address: jinhao_2004@126.com
  • Supported by:
    The National Natural Science Foundation of China (71473194); the Natural Science Foundation of Shaanxi Provincial Science and Technology Department (2020JM513).

摘要：

利用国家卫健委所公开的2021年12月12日至2022年12月12日的COVID-19全国整体感染人数以及无症状感染人数数据，讨论了COVID-19 全国无症状感染人数占整体感染人数比例的演变趋势。采用均值多变点模型及二元分割法，引入Ratio检验统计量并结合Block Bootstrap抽样方法，实证性的统计分析了观测数据的波动规律。研究结果表明：COVID-19全国无症状感染人数占整体感染人数比例总体呈显著上升趋势，具有高波动性和高跳跃性的特征。根据多变点位置估计方法，将数据分为5个阶段。在此基础上，探索不同阶段下数据变化与受感染毒株类型、气温、地区政策等因素之间的机理。

关键词: COVID-19, 无症状感染人数, 均值多变点模型, 变点检验, Block Bootstrap

Abstract:

Based on the data released by the National Health Commission on the total number of COVID-19 patients and the number of asymptomatic patients from December 12, 2021 to December 12, 2022, this paper discusses the evolving trend of the proportion of asymptomatic patients in the total number of COVID-19 patients. Using the mean multiple point model and binary segmentation method, the Ratio test statistic is introduced and the Block Bootstrap method is used to empirically analyze the fluctuation law of the observed data. The results showed that the proportion of asymptomatic infections in the total number of COVID-19 infections showed a significant upward trend, with high volatility and high jump characteristics. According to the multiple change point location estimation method, the data is divided into five stages. On this basis, the mechanism between the data changes and the types of infected strains, temperature, regional policies and other factors at different stages was explored.

Key words: COVID-19, number of asymptomatic patients, multivariable mean changes model, change point test, Block Bootstrap

中图分类号: