In Reply: I fully agree with Dr West that misinterpretation of P values may be at the root of several contradictions of postulated research findings. Indeed, medical research is increasingly conducted with very low prestudy odds of a true finding. This is a major problem in the molecular era of biomedicine that has been pointed out by several methodologists.1,2 I recently extended this framework3 to conclude that, under the current circumstances (considering typical prestudy odds, bias, number of teams working on a topic, and study design features), most published research findings are probably false.
Ioannidis JPA. Contradictions in Highly Cited Clinical Research—Reply. JAMA. 2005;294(21):2695–2696. doi:10.1001/jama.294.21.2696-a
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: