P-value discourse seems to focus on the hackable nature of significance testing. But shouldn't the bigger point that p-values are necessary but insufficient criteria? Being distinguishable from noise is the lowest possible form of scientific rigor.
-
Show this thread
-
Great scientists seem to get this. Herb Simon wrote about this in 1974: "In psychophysics... what is published is not the one-bit message that there is a relation... but the actual form of the function and the numerical values of its parameters."
1 reply 0 retweets 3 likesShow this thread
He also pointed out George Miller's influential "7 ± 2" paper cited 13 papers using parameter-estimation, and 2 papers using hypothesis-testing. It's not just about reproducibility -- history suggests that building actual models produces more *useful* results.
3:32 PM - 2 May 2020
0 replies
0 retweets
4 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
cognitive psychology. PhD