An answer on this question on the cross validated stack exchange compared statistical power to a microscope, such that "in order to see small things you need a powerful microscope" is analogous to "in order to detect small effects you need high statistical power." I have heard this before from a colleague and I have also used it elsewhere as a pedagogical device to much benefit.

Is there a primary source for this metaphor? Who came up with it first? Or is it just a meme whose creator is now a meme (pending answers to this question)?

  • 2
    $\begingroup$ Statistical power is affected chiefly by the size of the effect and the size of the sample used to detect it. Bigger effects are easier to detect than smaller effects, while large samples offer greater test sensitivity than small samples...so the metaphor of 'microscope' seems a bit out of phase...... $\endgroup$ – drvrm Jul 19 '18 at 11:33
  • $\begingroup$ "...out of phase..." #iseewhatyoudidthere $\endgroup$ – Carl Witthoft Jul 19 '18 at 13:14
  • $\begingroup$ If a thing is small then whatever that thing does is a small effect, so you need a powerful microscope to see it. If there's a large sample of that thing then you don't need as powerful of a microscope. $\endgroup$ – Jay Schyler Raadt Jul 19 '18 at 17:29
  • $\begingroup$ Jay, that's not the intent of the original text. (and not how statistics work) $\endgroup$ – Carl Witthoft Jul 20 '18 at 13:10
  • $\begingroup$ cross posted at math.stackexchange.com/questions/2856049/… $\endgroup$ – Glen_b Aug 4 '18 at 7:01

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.