Why is the statistical revolution not progressing? Vicious cycle of the scientific reform

Michal Bialek, Michał Misiak and Martyna Dziekan
Additional contact information
Michal Bialek: University of Waterloo
Michał Misiak: University of Wroclaw

No gmfs9, OSF Preprints from Center for Open Science

Abstract: To analyze the results of the research, behavioral scientists widely use a statistical rule that sets the significance level to 0.05. Recently, two recommendations on how to improve statistical inference were published: to redefine statistical significance to 0.005, and to select and justify the alpha. We analyzed the empirical work that cited the original recommendation papers, as well as the papers published by the scientist that co-authored the publications. About half of the numerous papers citing these recommendations adhered to them already in the first year since their publication. What is striking, the original authors that proposed the recommendations followed their own recommendations only in 6% of their empirical work. We surveyed the authors asking them to identify major obstacles they experienced while trying to implement their own recommendations, and obstacles they think others could expect or experience.

Date: 2021-09-23
New Economics Papers: this item is included in nep-sog
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://osf.io/download/614c71d615e9a4004b923c2f/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:osf:osfxxx:gmfs9

DOI: 10.31219/osf.io/gmfs9

Access Statistics for this paper

More papers in OSF Preprints from Center for Open Science
Bibliographic data for series maintained by OSF ().