Page 43 - 《武汉大学学报(信息科学版)》2025年第10期
P. 43
第 50 卷 第 10 期 武 汉 大 学 学 报( 信 息 科 学 版 ) Vol.50 No.10
2025 年 10 月 Geomatics and Information Science of Wuhan University Oct. 2025
引文格式:余航,王坚,王乐洋,等 . 接受域类型差异对多重备选假设数据探测法的影响分析[J]. 武汉大学学报(信息科学版),
2025,50(10):1978-1990.DOI:10.13203/j.whugis20240136
Citation:YU Hang,WANG Jian,WANG Leyang,et al. Impact of Different Types of Acceptance Regions on Data Snooping with
Multiple Alternative Hypotheses[J]. Geomatics and Information Science of Wuhan University, 2025, 50(10): 1978-1990. DOI:
10.13203/j.whugis20240136
接受域类型差异对多重备选假设数据探测法的
影响分析
余 航 王 坚 王乐洋 宁一鹏 赵 伟 1
3
2
1
4
1 苏州科技大学地理科学与测绘工程学院,江苏 苏州,215009
2 北京建筑大学测绘与城市空间信息学院,北京,100044
3 东华理工大学测绘与空间信息工程学院,江西 南昌,330013
4 山东建筑大学测绘地理信息学院,山东 济南,250101
摘 要:当先验单位权方差因子已知时,超椭球体或超多面体接受域常被用于多重备选假设数据探测法,以探测与识别
观测值中的粗差,但不同接受域类型对该方法的影响缺乏分析。首先,分别基于残差和闭合差构建的 Baarda w-检验统
计量,综合分析接受域类型的差异对检验空间、检验决策概率计算、最小可探测偏差(minimal detectable bias,MDB)及正
确识别率的影响,总结了目前 3 种计算检验决策概率的方法;然后,以二维闭合差的检验空间为基础,揭示了不同接受域
类型导致的正确识别率差异与函数模型几何间的对应关系。数值实验结果表明,不同接受域类型不仅会导致 MDB 的不
同,还会影响检验决策概率的大小,导致正确识别率存在差异。分析该差异与模型几何间的关系有助于改善网形设计,
降低接受域类型的差异对备选模型正确识别率的影响。
关键词:数据探测法;多重假设检验;检验空间;正确识别;最小可探测偏差
中图分类号:P207 文献标识码:A 收稿日期:2024‑09‑24
DOI:10.13203/j.whugis20240136 文章编号:1671‑8860(2025)10‑1978‑13
Impact of Different Types of Acceptance Regions on Data Snooping with
Multiple Alternative Hypotheses
YU Hang WANG Jian WANG Leyang NING Yipeng ZHAO Wei 1
2
4
3
1
1 School of Geography Science and Geomatics Engineering, Suzhou University of Science and Technology, Suzhou 215009, China
2 School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, China
3 School of Surveying and Geoinformation Engineering, East China University of Technology, Nanchang 330013, China
4 College of Surveying and Geo‑Informatics, Shandong Jianzhu University, Jinan 250101, China
Abstract: Objectives: When a priori variance factor is known, hyperellipsoidal or hyperpolyhedral accep‑
tance regions are frequently utilized for data snooping with multiple alternative hypotheses to pinpoint poten‑
tial outliers in the observations. Despite their prevalence, there is a dearth of research examining how these
regions affect the efficacy of data snooping. Methods: Residual- and misclosure-based Baarda w-test statis‑
tics are used to provide a comprehensive analysis of the impact of different acceptance regions on the testing
space, decision probabilities, the minimal detectable bias (MDB), and the probability of correctly identify‑
ing an alternative hypothesis. How the geometry of the functional model impacts the correct identification
probabilities is also used in a two-dimensional misclosure-based testing space. Results: The results show
that different types of acceptance regions have a certain impact on the size of the MDB and the testing deci‑
sion probabilities, but it is not significant. However, under certain geometric conditions, the variation in
correct identification probabilities is significant, with a theoretical difference of nearly 3% in single-point
基金项目:国家自然科学基金(42574064,42204011,42274029,42174011);江苏省科技计划项目(BK20230660)。
第一作者:余航,博士,讲师,研究方向为多源传感器融合及其质量控制。yhecit@163.com

