"Type I" and "Type II" errors, names first given by Jerzy Neyman and Egon Pearson to describe rejecting a null hypothesis when it's true and accepting one when it's not, are too vague for stat newcomers (and in general). This is better. [via]
via flowingdata.com
To this day I must think hard to figure out Type I and II errors.
Hat tip: Jayjit Roy
This picture makes one recognize that a visual image is so important for memory. As John noted in the post, he has to think hard each time about the differences.
And I did too until I finally realized that if I directly call up a visual image of two pdf’s instead of the verbal definition, it is easy. And also for another related function, the power of the test — I could never remember it until I began to call up the same visual image. Now it is easy. The original language of types of errors is totally non-intuitive.
Bio-stats pretty much uses the language of false positives and negatives. A better practice.
This is GREAT, since 1 is associate with male (now a falsely pregnant male) while 2 is female. Cool.
http://www.theguardian.com/books/2014/apr/04/why-all-love-numbers-mathematics
Leave a Reply