When economists analyze a well-conducted RCT or natural experiment and find a statistically significant effect, they conclude the null of no effect is unlikely to be true. But how frequently is this conclusion warranted? The answer depends on the proportion of tested nulls that are true and the power of the tests. I model the […]

The post How Credible is the Credibility Revolution? appeared first on Marginal REVOLUTION.

Comments In reply to Duh. Brothers, sisters, come sit, and gather ... by Equestrian * Another, comparing analyses by teams of the same sets of data, ... by mcint * Statistics are easily manipulated into superficially credible, ... by Statstats * So, are we pretending theres no selection into journals? by Duh * When using my preferred model, 87.3241% of papers in leading ... by How is this for credible? Related Stories Misandry * The Ball the Bat and the Hopeless * Did Katrina boost freedom, wreck state capacity, or both?