<?xml version="1.1" encoding="utf-8"?>
<article xsi:noNamespaceSchemaLocation="http://jats.nlm.nih.gov/publishing/1.1/xsd/JATS-journalpublishing1-mathml3.xsd" dtd-version="1.1" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><front><journal-meta><journal-id journal-id-type="publisher-id">ASDS</journal-id><journal-title-group><journal-title>Applied Statistics and Data Science</journal-title></journal-title-group><issn>3066-8433</issn><eissn>3066-8441</eissn><publisher><publisher-name>Art and Technology</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.61369/ASDS.2026100008</article-id><article-categories><subj-group subj-group-type="heading"><subject>Article</subject></subj-group></article-categories><title>一种稳健多变量自相关控制图设计方法及其在空气质量监控中的应用</title><url>https://artdesignp.com/journal/ASDS/2/10/10.61369/ASDS.2026100008</url><author>王志坚,张钰哲,杜玮</author><pub-date pub-type="publication-year"><year>2026</year></pub-date><volume>2</volume><issue>10</issue><history><date date-type="pub"><published-time>2026-10-20</published-time></date></history><abstract>传统VAR 控制图面对含异常值的多变量时间序列时，往往容易被个别异常点带偏，且往往无法准确指出所有发生异常的变量。监控结果一旦与真实情况错位，决策者就很难及时锁定并调整异常变量。针对这一短板，本文把稳健估计量与加权方法Zt 结合起来，构造了一种稳健VAR 控制图，并通过不同污染率、不同维度下的模拟实验检验其表现。结果显示，与原有方法相比，新控制图在异常识别的准确率和灵敏度上都有改善，异常值比例较高时优势更明显。这项工作为多变量时间序列监控增加了一种可选工具，也为数据驱动决策中的稳健性分析提供了参考。</abstract><keywords>向量自回归控制图,高维数据处理,异常值检测,过程控制</keywords></article-meta></front><body/><back><ref-list><ref id="B1" content-type="article"><label>1</label><element-citation publication-type="journal"><p>[1]Centofanti, Fabio, Antonio Lepore, Alessandra Menafoglio, Biagio Palumbo, and Simone Vantini. Functional Regression Control Chart[J]. Technometrics,2021,63(3):281&amp;ndash;94.
[2]Elisa C,E. R L. Robust multivariate control chart based on shrinkage for individual observations[J].Journal of Quality Technology,2022,54(4):415-440.[3]Bayati M ,Nasrollahzadeh S ,Moghadam B M . Robust Monitoring of Multivariate Location Using a New Nonparametric Depth ‐Based Control Chart[J].Journal of Applied Mathematics,2026,2026(1):1-13.[4]Pulido D J A ,Franco C E A ,G&amp;oacute;mez T G V . Nonparametric multivariate control chart with guaranteed in-control performance and cautious learning[J].Computers&amp;amp;Industrial Engineering,2026,218:112124.[5] 王志坚, 郑健松. 稳健Shewhart 控制图的构建及应用[J]. 统计与决策,2018,34 (24): 39-42.[6]AliH T ,SedeeqS B ,SalehM D , et al. Robust multivariate quality control charts for enhanced variability monitoring[J].Quality and Reliability Engineering Internation al,2023,40(3):1369-1381.[7]S V ,Sebastian N ,TA S . Robust Bivariate Control Chart for Process Monitoring with Rational Subgroups[J].Quality and Reliability Engineering International,2025,41(7):3232-3243.[8] 薛丽, 李聪凯, 贾元忠, 等.VSI 多变量自相关过程VAR 控制图经济设计[J]. 数理统计与管理,2023,42(04):626-636.[9]Capezza C, Centofanti F, Lepore A, etal. Functional regression control chart for monitoring ship CO2_2 emissions[J].Quality and Reliability Engineering Internation al,2022,38(3):1519-1537.[10]Will M ,Mark R . SampleQC: robust multivariate, multi-cell type, multi-sample quality control for single-cell data.[J].Genome biology,2023,24(1):1-22.[11] 雷彬文, 龚立雄. 多变量控制图及过程能力指数在生产中的应用[J]. 湖北工业大学学报,2023,38 (01):5-10.[12]Kalgonda, A. A., and S. R. Kulkarni. Multivariate Quality Control Chart for Autocorrelated Processes[J].Journal of Applied Statistics, 2004,31 (3):317&amp;ndash;327.[13]Hawkins, Douglas M. Multivariate Quality Control Based on Regression-Adiusted Variables[J].Technometrics,1991,33(1):61&amp;ndash;75.</p><pub-id pub-id-type="doi"/></element-citation></ref></ref-list></back></article>
