Extreme-value sampling design is cost-beneficial only with a valid statistical approach for exposure-secondary outcome association analyses

doi:10.1177/0962280219839093

CSpace

	Extreme-value sampling design is cost-beneficial only with a valid statistical approach for exposure-secondary outcome association analyses
	Zhang, Hang 1,2; Bi, Wenjian 3; Cui, Yuehua 4; Chen, Honglei 5; Chen, Jinbo 6; Zhao, Yanlong 1,2; Kang, Guolian 3
	2020-02-01
发表期刊	STATISTICAL METHODS IN MEDICAL RESEARCH
ISSN	0962-2802
卷号	29 期号:2 页码:466-480
摘要	In epidemiology cohort studies, exposure data are collected in sub-studies based on a primary outcome (PO) of interest, as with the extreme-value sampling design (EVSD), to investigate their correlation. Secondary outcomes (SOs) data are also readily available, enabling researchers to assess the correlations between the exposure and the SOs. However, when the EVSD is used, the data for SOs are not representative samples of a general population; thus, many commonly used statistical methods, such as the generalized linear model (GLM), are not valid. A prospective likelihood method has been developed to associate SOs with single-nucleotide polymorphisms under an extreme phenotype sequencing design. In this paper, we describe the application of the prospective likelihood method (STEVSD) to exposure-SO association analysis under an EVSD. We undertook extensive simulations to assess the performance of the STEVSD method in associating binary and continuous exposures with SOs, comparing it to the simple GLM method that ignores the EVSD. To demonstrate the cost-benefit of the STEVSD method, we also mimicked the design of two new retrospective studies, as would be done in actual practice, based on the PO of interest, which was the same as the SO in the EVSD study. We then analyzed these data by using the GLM method and compared its power to that of the STEVSD method. We demonstrated the usefulness of the STEVSD method by applying it to a benign ethnic neutropenia dataset. Our results indicate that the STEVSD method can control type I error well, whereas the GLM method cannot do so owing to its ignorance of EVSD, and that the STEVSD method is cost-effective because it has statistical power similar to that of two new retrospective studies that require collecting new exposure data for selected individuals.
关键词	Secondary outcome exposure extreme-value sampling design primary outcome cost-effective
DOI	10.1177/0962280219839093
收录类别	SCI
语种	英语
资助项目	American Lebanese Syrian Associated Charities (ALSAC) ; NHLBI at the NIH ; NIDDK at the NIH ; National Institutes of Health[HHSN268200782096C] ; National Institutes of Health[HHSN268201100011I] ; National Key Research and Development Program of China[2016YFB0901902] ; National Natural Science Foundation of China[61622309]
WOS研究方向	Health Care Sciences & Services ; Mathematical & Computational Biology ; Medical Informatics ; Mathematics
WOS类目	Health Care Sciences & Services ; Mathematical & Computational Biology ; Medical Informatics ; Statistics & Probability
WOS记录号	WOS:000513264200010
出版者	SAGE PUBLICATIONS LTD
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/50748
专题	中国科学院数学与系统科学研究院
通讯作者	Zhao, Yanlong; Kang, Guolian
作者单位	1.Chinese Acad Sci, Key Lab Syst & Control, Acad Math & Syst Sci, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Math Sci, Beijing, Peoples R China 3.St Jude Childrens Res Hosp, Dept Biostat, 332 N Lauderdale St, Memphis, TN 38105 USA 4.Michigan State Univ, Dept Stat & Probabil, E Lansing, MI 48824 USA 5.Michigan State Univ, Dept Epidemiol & Biostat, E Lansing, MI 48824 USA 6.Univ Penn, Dept Biostat Epidemiol & Informat, Philadelphia, PA 19104 USA
推荐引用方式 GB/T 7714	Zhang, Hang,Bi, Wenjian,Cui, Yuehua,et al. Extreme-value sampling design is cost-beneficial only with a valid statistical approach for exposure-secondary outcome association analyses[J]. STATISTICAL METHODS IN MEDICAL RESEARCH,2020,29(2):466-480.
APA	Zhang, Hang.,Bi, Wenjian.,Cui, Yuehua.,Chen, Honglei.,Chen, Jinbo.,...&Kang, Guolian.(2020).Extreme-value sampling design is cost-beneficial only with a valid statistical approach for exposure-secondary outcome association analyses.STATISTICAL METHODS IN MEDICAL RESEARCH,29(2),466-480.
MLA	Zhang, Hang,et al."Extreme-value sampling design is cost-beneficial only with a valid statistical approach for exposure-secondary outcome association analyses".STATISTICAL METHODS IN MEDICAL RESEARCH 29.2(2020):466-480.