Editing Winner's curse (section)

==Related uses==
{{Main|Regression toward the mean}}
The term ''winner's curse'' is also used in statistics to refer to the [[regression toward the mean]] phenomenon, particularly in [[genome-wide association studies]] and [[epidemiology]]. In studies involving many tests on one sample of the full population, the consequent stringent standards for significance make it likely that the first person to report a significant test (the ''winner'') will also report an [[effect size]] much larger than is likely to be seen in subsequent [[Replication (scientific method)|replication]] studies.<ref>{{cite journal |last=Ioannidis |first=John P. A. |year=2008 |title=Why most discovered true associations are inflated |journal=Epidemiology |volume=19 |issue=5 |pages=640–648 |doi=10.1097/EDE.0b013e31818131e7 |pmid= 18633328 |s2cid=15440816 |doi-access=free }}</ref><ref>{{Cite journal|last1=Palmer|first1=Cameron|last2=Pe’er|first2=Itsik|date=2017-07-17|title=Statistical correction of the Winner's Curse explains replication variability in quantitative trait genome-wide association studies|journal=PLOS Genetics|language=en|volume=13|issue=7|pages=e1006916|doi=10.1371/journal.pgen.1006916|issn=1553-7404|pmc=5536394|pmid=28715421 |doi-access=free }}</ref>