The regression trap and other pitfalls of replication science

• Verfasst von: Fiedler, Klaus [VerfasserIn]
• Verfasst von: Ziegler, Johannes [VerfasserIn]
• Titel: The regression trap and other pitfalls of replication science
• Titelzusatz: illustrated by the report of the open science collaboration
• Verf.angabe: Klaus Fiedler & Johannes Prager
• E-Jahr: 2018
• Jahr: 31 January 2018
• Umfang: 10 S.
• Fussnoten: Gesehen am 17.04.2020
• Titel Quelle: Enthalten in: Basic & applied social psychology
• Ort Quelle: New York, NY : Psychology Press, Taylor & Francis Group, 1980
• Jahr Quelle: 2018
• Band/Heft Quelle: 40(2018), 3, Seite 115-124
• ISSN Quelle: 1532-4834
• DOI: doi:10.1080/01973533.2017.1421953
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1694834964

Abstract

The Open Science Collaboration’s 2015 report suggests that replication effect sizes in psychology are modest. However, closer inspection reveals serious problems. When plotting replication effects are against original effects, the regression trap is lurking: Expecting replication effects to be equally strong as original effects is logically unwarranted; they are inevitably subject to regressive shrinkage. To control for regression, the reliability of original and replication studies must be taken into account. Further problems arise from missing manipulation checks and sampling biases. Our critical comment highlights the need for replication science to live up to the same methodological scrutiny as other research.