Restricted access

Purchase article

USD  $24.95

Student 1 year subscription

USD  $115.00

1 year subscription

USD  $153.00

Student 2 year subscription

USD  $218.00

2 year subscription

USD  $285.00

Background: It is not always clear whether physical activity is causally related to health outcomes, or whether the associations are induced through confounding or other biases. Randomized controlled trials of physical activity are not feasible when outcomes of interest are rare or develop over many years. Thus, we need methods to improve causal inference in observational physical activity studies. Methods: We outline a range of approaches that can improve causal inference in observational physical activity research, and also discuss the impact of measurement error on results and methods to minimize this. Results: Key concepts and methods described include directed acyclic graphs, quantitative bias analysis, Mendelian randomization, and potential outcomes approaches which include propensity scores, g methods, and causal mediation. Conclusions: We provide a brief overview of some contemporary epidemiological methods that are beginning to be used in physical activity research. Adoption of these methods will help build a stronger body of evidence for the health benefits of physical activity.

Lynch, Dixon-Suen, Yang, and English are with the Cancer Epidemiology Division, Cancer Council Victoria, Melbourne, VIC, Australia. Lynch, Yang, and English are also with the Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, University of Melbourne, Melbourne, VIC, Australia. Lynch is also with the Physical Activity Laboratory, Baker Heart and Diabetes Institute, Melbourne, VIC, Australia. Ramirez Varela is with the Postgraduate Program in Epidemiology, Federal University of Pelotas, Pelotas, Brazil; and the Postgraduate Program in Epidemiology, University of Los Andes, Bogota, Colombia. Ding is with the Prevention Research Collaboration, Sydney School of Public Health, University of Sydney, Sydney, NSW, Australia; and The Charles Perkins Centre, University of Sydney, Sydney, NSW, Australia. Gardiner is with the Centre for Health Services Research, The University of Queensland, Brisbane, QLD, Australia; and Mater Research Institute, The University of Queensland, Brisbane, QLD, Australia. Boyle is with the Australian Centre for Precision Health, School of Health Sciences, University of South Australia, Adelaide, SA, Australia.

Lynch (brigid.lynch@cancervic.org.au) is corresponding author.
  • 1.

    Kujala UM. Is physical activity a cause of longevity? It is not as straightforward as some would believe. A critical analysis. Br J Sports Med. 2018;52:914918. PubMed ID: 29545237. doi:10.1136/bjsports-2017-098639.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 2.

    Shiroma EJ, Lee IM. Can we proceed with physical activity recommendations if (almost) no clinical trial data exist on mortality? Br J Sports Med. 2018;52:888889. PubMed ID: 29545235. doi:10.1136/bjsports-2018-099185.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 3.

    Wade KH, Richmond RC, Davey Smith G. Physical activity and longevity: how to move closer to causal inference. Br J Sports Med. 2018;52:890891. PubMed ID: 29545236. doi:10.1136/bjsports-2017-098995.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 4.

    Lederer DJ, Bell SC, Branson RD, et al. Control of confounding and reporting of results in causal inference studies. Guidance for authors from editors of respiratory, sleep, and critical care journals. Ann Am Thorac Soc. 2019;16:2228. PubMed ID: 30230362. doi:10.1513/AnnalsATS.201808-564PS.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 5.

    Musci RJ, Stuart E. Ensuring causal, not casual, inference. Prev Sci. 2019;20:452456. PubMed ID: 30613853. doi:10.1007/s11121-018-0971-9.

  • 6.

    Bello NM, Ferreira VC, Gianola D, Rosa GJM. Conceptual framework for investigating causal effects from observational data in livestock. J Anim Sci. 2018;96:40454062. PubMed ID: 30107524. doi:10.1093/jas/sky277.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 7.

    Clare PJ, Dobbins TA, Mattick RP. Causal models adjusting for time-varying confounding-a systematic review of the literature. Int J Epidemiol. 2019;48:254265. PubMed ID: 30358847. doi:10.1093/ije/dyy218.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 8.

    Gage SH, Munafo MR, Davey Smith G. Causal inference in developmental origins of health and disease (DOHaD) research. Annu Rev Psychol. 2016;67:567585. PubMed ID: 26442667. doi:10.1146/annurev-psych-122414-033352.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 9.

    Greenland S, Pearl J, Robins JM. Causal diagrams for epidemiologic research. Epidemiology. 1999;10:3748. PubMed ID: 9888278. doi:10.1097/00001648-199901000-00008.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 10.

    Hernan MA, Hernandez-Diaz S, Werler MM, Mitchell AA. Causal knowledge as a prerequisite for confounding evaluation: an application to birth defects epidemiology. Am J Epidemiol. 2002;155:176184. PubMed ID: 11790682. doi:10.1093/aje/155.2.176.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 11.

    Ferguson KD, McCann M, Katikireddi SV, et al. Evidence synthesis for constructing directed acyclic graphs (ESC-DAGs): a novel and systematic method for building directed acyclic graphs [published online ahead of print October 24, 2019]. Int J Epidemiol. doi:10.1093/ije/dyz220

    • Search Google Scholar
    • Export Citation
  • 12.

    Hernán MA, Robins JM. Chapter 6 Graphical representation of causal effects. In: Hernán MA, Robins JM, eds. Causal Inference: What If. Boca Raton, FL: Chapman & Hall/CRC; 2019:6982. Available at https://www.hsph.harvard.edu/miguel-hernan/causal-inference-book/

    • Search Google Scholar
    • Export Citation
  • 13.

    Page A, Peeters G, Merom D. Adjustment for physical activity in studies of sedentary behaviour. Emerg Themes Epidemiol. 2015;12:10. PubMed ID: 26161129. doi:10.1186/s12982-015-0032-9.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 14.

    Shaw PA, Deffner V, Keogh RH, et al. Epidemiologic analyses with error-prone exposures: review of current practice and recommendations. Ann Epidemiol. 2018;28:821828. PubMed ID: 30316629. doi:10.1016/j.annepidem.2018.09.001.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 15.

    Lash TL, Fox MP, MacLehose RF, Maldonado G, McCandless LC, Greenland S. Good practices for quantitative bias analysis. Int J Epidemiol. 2014;43:19691985. PubMed ID: 25080530. doi:10.1093/ije/dyu149.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 16.

    Lash T, Fox M, Fink A. Applying Quantitative Bias Analysis to Epidemiologic Data. New York, NY: Springer; 2009.

  • 17.

    Mahmood S, Nguyen NH, Bassett JK, Macinnis RJ, Karahalios A, Bruinsma FJ, Owen N, Giles GG, Milne RL, English DR, Lynch BM. A quantitative bias analysis to estimate measurement error-related attenuation of the association between self-reported physical activity and colorectal cancer risk [published online ahead of print November 5, 2019]. Int J Epidemiol. pii: dyz209. doi:10.1093/ije/dyz209.

    • PubMed
    • Search Google Scholar
    • Export Citation
  • 18.

    Doherty A, Smith-Byrne K, Ferreira T, Holmes MV, Holmes C, Pulit SL, Lindgren CM. GWAS identifies 14 loci for device-measured physical activity and sleep duration. Nat Commun. 2018;9:5257. PubMed ID: 30531941. doi:10.1038/s41467-018-07743-4.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 19.

    Klimentidis YC, Raichlen DA, Bea J, et al. Genome-wide association study of habitual physical activity in over 377,000 UK Biobank participants identifies multiple variants including CADM2 and APOE. Int J Obes. 2018;42(6):11611176. PubMed ID: 29899525. doi:10.1038/s41366-018-0120-3.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 20.

    Pearce N, Lawlor DA. Causal inference-so much more than statistics. Int J Epidemiol. 2016;45:18951903. PubMed ID: 28204514. doi:10.1093/ije/dyw328.

  • 21.

    Pearl J, Mackenzie D. The Book of Why: The New Science of Cause and Effected. London, UK: Allen Lane; 2018:2352.

  • 22.

    Williamson E, Morley R, Lucas A, Carpenter J. Propensity scores: from naive enthusiasm to intuitive understanding. Stat Methods Med Res. 2012;21:273293. PubMed ID: 21262780. doi:10.1177/0962280210394483.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 23.

    Naimi AI, Cole SR, Kennedy EH. An introduction to g methods. Int J Epidemiol. 2017;46:756762. PubMed ID: 28039382. doi:10.1093/ije/dyx086.

    • Search Google Scholar
    • Export Citation
  • 24.

    Robins JM, Hernán MA. Estimation of the causal effects of time-varying exposures. In: Fitzmaurice G, Davidian M, Verbeke G, Molenberghs G, eds. Longitudinal Data Analysis. Boca Raton, FL: Taylor & Francis Group; 2009:553599.

    • Search Google Scholar
    • Export Citation
  • 25.

    VanderWeele TJ. Explanation in Causal Inference: Methods for Mediation and Interactioned. New York, NY: Oxford University Press; 2015.

All Time Past Year Past 30 Days
Abstract Views 470 470 27
Full Text Views 613 613 8
PDF Downloads 187 187 5