A note on tests for relevant differences with extremely large sample sizes

Callegaro, Andrea;Ndour, Cheikh;Aris, Emmanuel;Legrand, Catherine
(2019) Biometrical Journal : journal of mathematical methods in biosciences — Vol. 61, n° 1, p. 162-165 (2019)

Files

ISBARP_2019_08_Legrand_Anoteontestsforrelevantdifferenceswithextremelylargesamplesizes_dial.pdf
  • Open Access
  • Adobe PDF
  • 146.14 KB
Download

Details

Authors
  • Callegaro, Andreaorcid-logo
    Author
  • Ndour, CheikhUCLouvain
    Author
  • Aris, Emmanuel
    Author
  • Legrand, CatherineUCLouvain
    Author
Abstract
A well-known problem in classical two-tailed hypothesis testing is that P-values go to zero when the sample size goes to infinity, irrespectively of the effect size. This pitfall can make the testing of data consisting of large sample sizes potentially unreliable. In this note, we propose to test for relevant differences to overcome this issue. We illustrate the proposed test a on real data set of about 40 million privately insured patients.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Callegaro, A., Ndour, C., Aris, E., & Legrand, C. (2019). A note on tests for relevant differences with extremely large sample sizes. Biometrical Journal : journal of mathematical methods in biosciences, 61(1), 162-165. https://doi.org/10.1002/bimj.201800195 (Original work published 2019)