May the power be with you: are there highly powered studies in neuroscience, and how can we get more of them?

Algermissen, Johannes and Mehler, David 2018. May the power be with you: are there highly powered studies in neuroscience, and how can we get more of them? Journal of Neurophysiology 119 (6) , pp. 2114-2117. 10.1152/jn.00765.2017

Preview

PDF - Accepted Post-Print Version Download (231kB) | Preview

Abstract

Statistical power is essential for robust science and replicability, but a meta-analysis by Button et al. in 2013 diagnosed a "power failure" for neuroscience. In contrast, Nord et al. (J Neurosci 37: 8051-8061, 2017) re-analyzed these data and suggested that some studies feature high power. We illustrate how publication and researcher bias might have inflated power estimates, and review recently introduced techniques that can improve analysis pipelines and increase power in neuroscience studies.

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Psychology
Publisher:	American Physiological Society
ISSN:	0022-3077
Date of First Compliant Deposit:	19 March 2018
Date of Acceptance:	14 February 2018
Last Modified:	14 Nov 2024 07:00
URI:	https://orca.cardiff.ac.uk/id/eprint/109973

Citation Data

Cited 22 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item