Object of Inquiry: Psychology’s Other (Non-replication) Problem
- 12 Downloads
Ever since the 2005 publication of a landmark paper “Why Most Published Research Findings Are False” by medical statistician John Ioannidis,1 social and biomedical science has been stumbling through what is now termed the “Irreproducibility Crisis.”2 The “crisis” refers to the failure to get the same results when supposedly reliable, “statistically significant” studies are repeated.
The crisis is a legacy of what has become the dominant experimental method in social and biomedical science, establishing a true effect by comparing two or more groups of subjects each exposed to a different experimental manipulation. In this article I argue that remedies proposed for this problem miss an important point. The problem is not just the statistical reliability—repeatability—of group results, which is already being improved. An equally important problem is drawing conclusions about the psychology or physiology of individuals from group averages.
The aim of basic research in biomedicine and...