Overview

data dredging


Show Summary Details

Quick Reference

An unkind description of the conduct of a desperate or dishonest investigator who attempts to demonstrate a “significant” result by using a sequence of statistical tests that were not in the original research protocol. This conduct has been summed up in the remark: “If you torture the data enough, they'll confess to anything!” Not to be confused with data mining.

Subjects: Public Health and Epidemiology.


Reference entries

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.