Testing unit root non-stationarity in the presence of missing data in univariate time series of mobile health studies.

IF 1 4区 数学 Q3 STATISTICS & PROBABILITY
Charlotte Fowler, Xiaoxuan Cai, Justin T Baker, Jukka-Pekka Onnela, Linda Valeri
{"title":"Testing unit root non-stationarity in the presence of missing data in univariate time series of mobile health studies.","authors":"Charlotte Fowler, Xiaoxuan Cai, Justin T Baker, Jukka-Pekka Onnela, Linda Valeri","doi":"10.1093/jrsssc/qlae010","DOIUrl":null,"url":null,"abstract":"<p><p>The use of digital devices to collect data in mobile health studies introduces a novel application of time series methods, with the constraint of potential data missing at random or missing not at random (MNAR). In time-series analysis, testing for stationarity is an important preliminary step to inform appropriate subsequent analyses. The Dickey-Fuller test evaluates the null hypothesis of unit root non-stationarity, under no missing data. Beyond recommendations under data missing completely at random for complete case analysis or last observation carry forward imputation, researchers have not extended unit root non-stationarity testing to more complex missing data mechanisms. Multiple imputation with chained equations, Kalman smoothing imputation, and linear interpolation have also been used for time-series data, however such methods impose constraints on the autocorrelation structure and impact unit root testing. We propose maximum likelihood estimation and multiple imputation using state space model approaches to adapt the augmented Dickey-Fuller test to a context with missing data. We further develop sensitivity analyses to examine the impact of MNAR data. We evaluate the performance of existing and proposed methods across missing mechanisms in extensive simulations and in their application to a multi-year smartphone study of bipolar patients.</p>","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":null,"pages":null},"PeriodicalIF":1.0000,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11175825/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Royal Statistical Society Series C-Applied Statistics","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.1093/jrsssc/qlae010","RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/6/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"STATISTICS & PROBABILITY","Score":null,"Total":0}
引用次数: 0

Abstract

The use of digital devices to collect data in mobile health studies introduces a novel application of time series methods, with the constraint of potential data missing at random or missing not at random (MNAR). In time-series analysis, testing for stationarity is an important preliminary step to inform appropriate subsequent analyses. The Dickey-Fuller test evaluates the null hypothesis of unit root non-stationarity, under no missing data. Beyond recommendations under data missing completely at random for complete case analysis or last observation carry forward imputation, researchers have not extended unit root non-stationarity testing to more complex missing data mechanisms. Multiple imputation with chained equations, Kalman smoothing imputation, and linear interpolation have also been used for time-series data, however such methods impose constraints on the autocorrelation structure and impact unit root testing. We propose maximum likelihood estimation and multiple imputation using state space model approaches to adapt the augmented Dickey-Fuller test to a context with missing data. We further develop sensitivity analyses to examine the impact of MNAR data. We evaluate the performance of existing and proposed methods across missing mechanisms in extensive simulations and in their application to a multi-year smartphone study of bipolar patients.

测试移动健康研究单变量时间序列中存在缺失数据时的单位根非平稳性。
在移动健康研究中,使用数字设备收集数据为时间序列方法带来了一种新的应用,即潜在的随机或非随机数据缺失(MNAR)。在时间序列分析中,静态检验是一个重要的初步步骤,可为适当的后续分析提供依据。Dickey-Fuller 检验是在无缺失数据的情况下,对单位根非平稳性的零假设进行评估。除了针对完整病例分析或最后观察结转估算的完全随机缺失数据提出建议外,研究人员还没有将单位根非平稳性检验扩展到更复杂的缺失数据机制。链式方程多重归因、卡尔曼平滑归因和线性插值也被用于时间序列数据,但这些方法对自相关结构施加了限制,影响了单位根检验。我们提出了使用状态空间模型方法进行最大似然估计和多重估算的方法,以将增强的 Dickey-Fuller 检验调整到有缺失数据的情况下。我们进一步开发了敏感性分析,以检验 MNAR 数据的影响。我们通过大量模拟,并将其应用于一项针对双相情感障碍患者的多年期智能手机研究中,评估了现有方法和拟议方法在不同缺失机制下的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
2.50
自引率
0.00%
发文量
76
审稿时长
>12 weeks
期刊介绍: The Journal of the Royal Statistical Society, Series C (Applied Statistics) is a journal of international repute for statisticians both inside and outside the academic world. The journal is concerned with papers which deal with novel solutions to real life statistical problems by adapting or developing methodology, or by demonstrating the proper application of new or existing statistical methods to them. At their heart therefore the papers in the journal are motivated by examples and statistical data of all kinds. The subject-matter covers the whole range of inter-disciplinary fields, e.g. applications in agriculture, genetics, industry, medicine and the physical sciences, and papers on design issues (e.g. in relation to experiments, surveys or observational studies). A deep understanding of statistical methodology is not necessary to appreciate the content. Although papers describing developments in statistical computing driven by practical examples are within its scope, the journal is not concerned with simply numerical illustrations or simulation studies. The emphasis of Series C is on case-studies of statistical analyses in practice.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信