Advertisement

European Journal of Epidemiology

, Volume 33, Issue 5, pp 501–502 | Cite as

Toward eradicating misconceptions on matching in etiological studies

  • Igor Karp
CORRESPONDENCE

I read with great interest a scholarly essay by Mansournia, Jewell, and Greenland (MJG) on case–control matching [1]. I applaud the authors’ efforts, but I believe eradication of misonceptions surrounding the topic of matching requires a more radical measure—namely, abandonment of the commonly perceived (yet conceptually untenable) duality of the principal types of etiologic study: the ‘cohort’ study and the ‘case–control’ study [2]. But if one is not prepared to leave this duality behind, I believe it important to at least adopt the modern conceptions of these studies, as their original conceptions have considerably evolved in the last few decades [2, 3].

MJG do not define ‘cohort’ or ‘case–control’ studies in their essay, and although they do mention “many protocols for selecting controls,” the fact that the authors view ‘cohort matching’ as matching “across exposure groups” and case–control matching as matching “across outcome groups” and do not invoke the centrally-important...

References

  1. 1.
    Mansournia MA, Jewell NP, Greenland S. Case–control matching: effects, misconceptions, and recommendations. Eur J Epidemiol. 2017.  https://doi.org/10.1007/s10654-017-0325-0.PubMedGoogle Scholar
  2. 2.
    Miettinen OS, Karp I. Epidemiological Research: An Introduction. Dordrecht: Springer; 2012.CrossRefGoogle Scholar
  3. 3.
    Karp I, Miettinen OS. On the essentials of etiological research for preventive medicine. Eur J Epidemiol. 2014;29:455–7.CrossRefPubMedGoogle Scholar
  4. 4.
    Porta M (Editor), Greenland S, Last JM (Associate Editors). A dictionary of epidemiology. 5th ed. Oxford: Oxford University Press; 2008.Google Scholar
  5. 5.
    Karp I. Confounding of incidence density ratio in case–control studies. Epidemiology. 2013;24:627.CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media B.V., part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Epidemiology and Biostatistics, Schulich School of Medicine and DentistryUniversity of Western OntarioLondonCanada

Personalised recommendations