“p-hacking” – I Fooled Millions Into Thinking Chocolate Helps Weight Loss

Hacking experimental design to achieve statistical significance:

It’s called p-hacking—fiddling with your experimental design and data to push p under 0.05—and it’s a big problem. Most scientists are honest and do it unconsciously. They get negative results, convince themselves they goofed, and repeat the experiment until it “works”. Or they drop “outlier” data points.

via I Fooled Millions Into Thinking Chocolate Helps Weight Loss. Here’s How..

Advertisements