Using negative controls to adjust for unmeasured confounding bias in time series studies

被引:1
|
作者
Hu, Jie Kate [1 ]
Tchetgen Tchetgen, Eric J. [2 ]
Dominici, Francesca [1 ]
机构
[1] Harvard TH Chan Sch Publ Hlth, Dept Biostat, Boston, MA 02120 USA
[2] Univ Penn, Wharton Sch, Dept Stat & Data Sci, Philadelphia, PA USA
来源
NATURE REVIEWS METHODS PRIMERS | 2023年 / 3卷 / 01期
基金
美国国家卫生研究院;
关键词
PARTICULATE AIR-POLLUTION; CASE-CROSSOVER; HOSPITAL ADMISSIONS; CAUSAL INFERENCE; PROPENSITY SCORE; MENTAL-HEALTH; GREEN SPACES; MORTALITY; EXPOSURE; IDENTIFICATION;
D O I
10.1038/s43586-023-00249-4
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Unmeasured confounding threatens the validity of observational studies. Negative control variables (NCs) are variables that either do not cause the outcome of interest or are not caused by the exposure of interest and are increasingly available from emerging sensing technologies and digitized health records. Under appropriate assumptions, NCs can be used to adjust for unmeasured confounding bias. This Primer explains the assumptions and implementation of NCs for unmeasured confounding bias adjustment. Among the method's broad applications in public health research, time series studies of environmental exposures - air pollution, wildfires and heat - and health outcomes are focused on. Three types of unmeasured confounding in time series studies are considered: time-invariant confounders with time-invariant confounding effects; time-invariant confounders with time-modified confounding effects; and time-varying confounders with immediate and/or lagged confounding effects. For each type of confounding, guidance is provided on how to select NCs using several case studies. Finally, challenges and opportunities are described, to help catalyse additional methodological developments. Negative control variables (NCs) are variables that do not cause the outcome of interest and are not caused by the exposure of interest. This Primer describes how to use NCs to adjust for unmeasured confounding bias, for example in environmental or public health studies.
引用
收藏
页数:14
相关论文
共 50 条
  • [2] Using negative controls to adjust for unmeasured confounding bias in time series studies
    Jie Kate Hu
    Eric J. Tchetgen Tchetgen
    Francesca Dominici
    [J]. Nature Reviews Methods Primers, 3
  • [3] The Search for Truth Amidst the Bias Addressing Unmeasured Confounding in Observational Studies Addressing Unmeasured Confounding in Observational Studies
    Li, Hu
    Zhang, Xiang
    Faries, Douglas E.
    Stamey, James
    Imbens, Guido W.
    [J]. PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2017, 26 : 88 - 88
  • [4] Negative Controls A Tool for Detecting Confounding and Bias in Observational Studies
    Lipsitch, Marc
    Tchetgen, Eric Tchetgen
    Cohen, Ted
    [J]. EPIDEMIOLOGY, 2010, 21 (03) : 383 - 388
  • [5] Identification and estimation of causal peer effects using double negative controls for unmeasured network confounding
    Egami, Naoki
    Tchetgen, Eric J. Tchetgen
    [J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2024, 86 (02) : 487 - 511
  • [6] Using expert opinion to quantify unmeasured confounding bias parameters
    Soodabeh Navadeh
    Ali Mirzazadeh
    Willi McFarland
    Sarah Woolf-King
    Mohammad Ali Mansournia
    [J]. Canadian Journal of Public Health, 2016, 107 (1) : e43 - e48
  • [7] Using expert opinion to quantify unmeasured confounding bias parameters
    Navadeh, Soodabeh
    Mirzazadeh, Ali
    McFarland, Willi
    Woolf-King, Sarah
    Mansournia, Mohammad Ali
    [J]. CANADIAN JOURNAL OF PUBLIC HEALTH-REVUE CANADIENNE DE SANTE PUBLIQUE, 2016, 107 (01): : E43 - E48
  • [8] Adjusting for bias and unmeasured confounding in Mendelian randomization studies with binary responses
    Palmer, Tom M.
    Thompson, John R.
    Tobin, Martin D.
    Sheehan, Nuala A.
    Burton, Paul R.
    [J]. INTERNATIONAL JOURNAL OF EPIDEMIOLOGY, 2008, 37 (05) : 1161 - 1168
  • [9] Using Simulation to Explore the Properties of IV Bias Amplification and Unmeasured Confounding
    Todd, Jonathan V.
    Brookhart, M. Alan
    [J]. PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2014, 23 : 31 - 31
  • [10] Unmeasured confounding in nonrandomized studies: quantitative bias analysis in health technology assessment
    Leahy, Thomas P.
    Kent, Seamus
    Sammon, Cormac
    Groenwold, Rolf H. H.
    Grieve, Richard
    Ramagopalan, Sreeram
    Gomes, Manuel
    [J]. JOURNAL OF COMPARATIVE EFFECTIVENESS RESEARCH, 2022, 11 (12) : 851 - 859