In his book Flaw of Averages, Sam Savage describes the IOT test of statistical significance.
Joe Berkson, a statistician at the Mayo Clinic, developed his own criterion, which he termed the IOT Test, or Inter Ocular Trauma Test, requiring a graph that hit you between the eyes.
We have a similar sounding but little used method* called “The Squinty Eye Test” (1) I might have to check out that book and see if it’s related.
* very very little used. ;-)
I have heard it called the inter-occular stress test.
We have (quite seriously) adopted the K-test in our lab. A finding is significant only when the wife of a colleague can see the effect. Her name starts with a …. K
This in economics is the HT (hunting test). Where one
application misses by 1m to the right and the next by 1m to
the left, we declare having hit our target.
Seriously, this is not be as bad as it sounds
as we have a weighting system (the DW) for the distance
from the target. DW stands for ‘dismal weight’ which is
where the discipline gets its reputation as the dismal science.
I was taught a similar test as a student:
The Inter Ocular Impact Factor (IOIF).
Since journals “create” their impact factors by deciding what to publish and what not to publish – an “Inter-Ocular Impact factor” seems a logical statistic for manuscripts in such journals.
I believe the IOIF is a cousin of GIGO.
that this test
I learnt if as the Inter Ocular Effect
I learned it, as well, as “The interocular Trauma Effect” from Willard Runquist around 1971 or so, and have taught many of my students since.
The sense and sensibility of the IOT was discussed in the University of Minnesota’s graduate-level stat curriculum in the 1960s. It was usually a preamble to discussing Tukey’s Quick Compact Two-Sample Test to Duckworth’s Specifications.