• Christopher R Hill, Stephen Samendinger, and Amanda M Rymal.
• Department of Kinesiology, California State University, San Bernardino, 5500 University Parkway, San Bernardino, CA, USA.
• Ann Behav Med. 2021 Jun 2; 55 (6): 543-556.

BackgroundPractitioners and researchers may not always be able to adequately evaluate the evidential value of findings from a series of independent studies. This is partially due to the possibility of inflated effect size estimates for these findings as a result of researcher manipulation or selective reporting of analyses (i.e., p-hacking). In light of the possible overestimation of effect sizes in the literature, the p-curve analysis has been proposed as a worthwhile tool that may help identify bias across a series of studies focused on a single effect. The p-curve analysis provides a measure of the evidential value in the published literature and might highlight p-hacking practices.PurposeTherefore, the purpose of this paper is to introduce the mechanics of the p-curve analysis to individuals researching phenomena in the psychosocial aspects of behavior and provide a substantive example of a p-curve analysis using findings from a series of studies examining a group dynamic motivation gain paradigm.MethodsWe performed a p-curve analysis on a sample of 13 studies that examined the Köhler motivation gain effect in exercise settings as a means to instruct readers how to conduct such an analysis on their own.ResultsThe p-curve for studies examining the Köhler effect demonstrated evidential value and that this motivation effect is likely not a byproduct of p-hacking. The p-curve analysis is explained, as well as potential limitations of the analysis, interpretation of the results, and other uses where a p-curve analysis could be implemented.© Society of Behavioral Medicine 2020. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

13 keywords...

hide…