Endgames Statistical question

Uncontrolled studies

BMJ 2009; 338 doi: http://dx.doi.org/10.1136/bmj.b1164 (Published 26 March 2009) Cite this as: BMJ 2009;338:b1164
  1. John Fletcher, clinical epidemiologist
  1. 1BMJ, London WC1H 9JR
  1. jfletcher{at}bmj.com

    To measure the effect of a food supplement on headaches, a questionnaire survey was sent to a random sample of workers in one factory. People who scored in the top 20% for frequency of headaches in the previous two weeks were invited to “try a natural food supplement used to treat headaches.” A follow-up questionnaire two weeks later showed markedly fewer headaches. Which, if any, of the following could affect the results?

    • a) The Hawthorne effect

    • b) Regression to the mean

    • c) Healthy worker effect

    • d) Placebo effect

    • e) Confounding by indication

    Answer

    a, b, d—A factory called the Hawthorne Works was …

    View Full Text

    Sign in

    Log in through your institution

    Free trial

    Register for a free trial to thebmj.com to receive unlimited access to all content on thebmj.com for 14 days.
    Sign up for a free trial

    Subscribe