R 2 should not be used to describe behavioral‐economic discounting and demand models
Journal of the Experimental Analysis of Behavior · 2024-09 · 122 (2) · 117-138
DOI: 10.1002/jeab.4200 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Experimental Analysis of Behavior, online erschienen am 19.08.2024. Verfasst von Brett W Gelino und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry and Behavioral Sciences, Johns Hopkins University School of Medicine, Baltimore, MD, USA. Hauptthemen laut MEDLINE: Economics, Behavioral. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 126 Literaturangaben. Gefördert von: National Institute on Drug Abuse (NIDA) of the National Institutes of Health.
Abstract (Originalsprache)
Literature concerning operant behavioral economics shows a strong preference for the coefficient of determination ( R 2 ) metric to (a) describe how well an applied model accounts for variance and (b) depict the quality of collected data. Yet R 2 is incompatible with nonlinear modeling. In this report, we provide an updated discussion of the concerns with R 2 . We first review recent articles that have been published in the Journal of the Experimental Analysis of Behavior that employ nonlinear models, noting recent trends in goodness‐of‐fit reporting, including the continued reliance on R 2 . We then examine the tendency for these metrics to bias against linear‐like patterns via a positive correlation between goodness of fit and the primary outputs of behavioral‐economic modeling. Mathematically, R 2 is systematically more stringent for lower values for discounting parameters (e.g., k ) in discounting studies and lower values for the elasticity parameter (α) in demand analysis. The study results suggest there may be heterogeneity in how this bias emerges in data sets of varied composition and origin. There are limitations when using any goodness‐of‐fit measure to assess the systematic nature of data in behavioral‐economic studies, and to address those we recommend the use of algorithms that test fundamental expectations of the data.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Psychiatry and Behavioral Sciences, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
- Sheppard Pratt Center of Excellence in Psilocybin Research and Treatment, Baltimore, MD, USA.
ORCID-Profile: Brett W Gelino, Justin C Strickland, Matthew W Johnson
Förderung
- National Institute on Drug Abuse (NIDA) of the National Institutes of Health
Zitieren
APA
Gelino, B. W., Strickland, J. C., & Johnson, M. W. (2024). R 2 should not be used to describe behavioral‐economic discounting and demand models. Journal of the Experimental Analysis of Behavior, 122(2), 117-138. https://doi.org/10.1002/jeab.4200
Vancouver
Gelino BW, Strickland JC, Johnson MW. R 2 should not be used to describe behavioral‐economic discounting and demand models. Journal of the Experimental Analysis of Behavior. 2024;122(2):117-138. doi:10.1002/jeab.4200
BibTeX
@article{Gelino2024,
author = {Gelino, Brett W and Strickland, Justin C and Johnson, Matthew W},
title = {R 2 should not be used to describe behavioral‐economic discounting and demand models},
journal = {Journal of the Experimental Analysis of Behavior},
year = {2024},
volume = {122},
number = {2},
pages = {117--138},
doi = {10.1002/jeab.4200}
}
EUVIMED