"... there is a fundamental disconnect between the kind of evidence that reassures human beings and the kind of evidence that the laws of statistics and science allow us to collect.
There is a joke among epidemiologists that encapsulates this disconnect: the marriage vow between two epidemiologists goes "I promise to always fail to reject you." There is a reason why this is funny (to at least some of us). ..."
... from page 248 of Denying to the Grave: Why we ignore the facts that will save us by Sara E Gorman & Jack M Gorman (2017).
Funny? As the parenthetical aside suggests, perhaps mainly to epidemiologists and statisticians (based on a non-representative sample of N = 5 taken yesterday). What's the joke referring to? It's about the non-intuitive process of testing a hypothesis against experimental data. In brief, thinking is hard – especially when doing rigorous analysis of noisy, incomplete samples. Most of the time the evidence doesn't tell us what we want to know, namely causal relationships; it tells us how likely we might have seen this result purely by chance.
And marriage is hard too!
(cf Medicine and Statistics (2010-11-13), Statistical Hypothesis Inference Testing (2013-12-01), P-Hacking (2014-09-20), Ten Common Statistical Mistakes (2019-10-14), ...) - ^z - 2024-04-27