• howrar@lemmy.ca
    link
    fedilink
    English
    arrow-up
    3
    ·
    12 days ago

    Observational epidemiology […] should only be used to generate hypothesis and design interventional studies.

    I feel like I’ve seen this same thing said at least three times in the past few days. It used to be that we all just went “correlation does not imply causation”. What changed?

    • jet@hackertalks.com
      link
      fedilink
      English
      arrow-up
      1
      ·
      12 days ago

      There are many people who would rather use correlation to push their philosophy then doing the work of a interventional study.

      The risk of doing the actual falsifiable experiment is your hypothesis might be wrong