Photo: PLOS Video Channel, CC BY 3.0, Wikimedia Commons
John Ioannidis
Stanford University
- Research field
- Meta-research, epidemiology, evidence-based medicine
John Ioannidis is a physician and professor of medicine and of epidemiology and population health at Stanford University, and one of the founders of meta-research, the study of how research is done. His 2005 essay turned the significance level and the power of a test into the probability that a published significant finding is true, and showed that in fields with small studies, small effects, many tested hypotheses, and flexible analyses that probability can fall below one half. The unit presents this calculation right after the two kinds of error, as the first consequence of running many tests at the 5 per cent level.
In the masterclass
Section 3, after the power section, turns the type I and type II error rates into the probability that a significant finding is true.
The research is presented in Unit 7: Hypothesis Tests and p-Values, in a research spotlight box that explains the result at the level of the unit and links it to what you have just learned.