The message you see in theiusimus machines that the completely look like women are taller than men, but that result given that there only, it had to be a very big difference given the size of the sample. With a small sample, the more likely it is what you found literally isn't true. So when economists find statistically significant results at small samples, and the definition of small here is gonna be essentially underpowered, they're gonna say, hey, look how great this result is because it's even true in a small sample. And then you come along and Andrew Gellman and others and say, actually it's the opposite.
John Ioannidis of Stanford University talks with EconTalk host Russ Roberts about his research on the reliability of published research findings. They discuss Ioannidis's recent study on bias in economics research, meta-analysis, the challenge of small sample analysis, and the reliability of statistical significance as a measure of success in empirical research.