(This article was originally published at Statistical Modeling, Causal Inference, and Social Science, and syndicated at StatsBlogs.)
Paul Alper sends along this inspiring story of Julie Miller, a heroic triathlete who just wants to triathle in peace, but she keeps getting hassled by the replication police. Those shameless little bullies won’t let her just do her thing, instead they harp on technicalities like missing timing clips and crap like that. Who cares about missing timing clips? Her winning times were statistically significant, that’s what matters to me. And her recorded victories were peer reviewed. But, no, those second stringers can’t stop with their sniping.
I for one don’t think this running star should resist any calls for her to replicate her winning triathlon times. The replication rate of those things is statistically indistinguishable from 100%, after all! Track and field has become preoccupied with prevention and error detection—negative psychology—at the expense of exploration and discovery.
In fact, I’m thinking the American Statistical Association could give this lady the Founders Award, which hasn’t really had a worthy recipient since 2002.
The post Shameless little bullies claim that published triathlon times don’t replicate appeared first on Statistical Modeling, Causal Inference, and Social Science.
Please comment on the article here: Statistical Modeling, Causal Inference, and Social Science
