Thinking, Fast and Slow · chapter 10 · id thinking-fast-and-slow-c10-03-many-of-the-psychology-studies

“Many of the psychology studies Kahneman cites in this book -- including studies on priming and social psychology -- were themselves conducted with small samples, making them vulnerable to the exact error this chapter describes.”

holdsconfidence: high✓ ZHP-verified + red-teamed

Receipts

Ioannidis (2005), PLoS Medicine 2(8)DOI registry: valid

For most study designs, the post-study probability that a statistically significant finding reflects a true effect is less than 50%. Small sample sizes, flexible designs, and publication bias are key contributors.

Open Science Collaboration (2015), Science 349(6251)DOI registry: valid

Attempting to replicate 100 psychology studies, only 36% produced statistically significant results in the replication, compared to 97% in the originals. Social priming studies had among the lowest replication rates.

Button et al. (2013), Nature Reviews Neuroscience 14DOI registry: valid

Median statistical power across neuroscience studies is ~21%, meaning most studies are underpowered and published significant results are likely to be inflated (winner's curse).

This claim is a stable, citable object. If you can falsify a verdict, tell us — corrections are loud here.