Beyond the basics: Using nonlinear approaches to classical statistical tests to improve fit and interpretability
PLOS One · 17.11.2026 · 21 (11) · e0362851
DOI: 10.1371/journal.pone.0362851 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 17.11.2026. Verfasst von Timothy E O'Brien und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics and Statistics, Loyola University Chicago, Chicago, Illinois, United States of America. Hauptthemen laut MEDLINE: Nonlinear Dynamics, Models, Statistical. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Nonlinear models are less familiar to practitioners and can appear intimidating. However, nonlinear models often fit data better and, critically, may improve interpretability. Our previous work gave a simple introduction to nonlinear regression modeling, providing simple and straightforward examples and underscored the superiority of likelihood methods in obtaining confidence intervals. The current manuscript extends this introduction and shows how classic linear models — such as paired t-tests, analysis of covariance (ANCOVA), two-way ANOVA, and logistic regression — can benefit from using a nonlinear approach to fitting the data. Here we introduce, explore and discuss several of these approaches using important examples which highlight the benefits of the nonlinear methodology to the data analysis. As demonstrated herein, these benefits include (but are not limited to) providing additional insights into the process underlying the data, more appropriate model fit of the data, and more directly addressing the research questions. The provided R code can be adapted for use.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Mathematics and Statistics, Loyola University Chicago, Chicago, Illinois, United States of America.
- Department of Psychology, University of South Florida, Tampa, Florida, United States of America.
ORCID-Profile: Timothy E O'Brien
Zitieren
APA
O'Brien, T. E., & Silcox, J. W. (2026). Beyond the basics: Using nonlinear approaches to classical statistical tests to improve fit and interpretability. PLOS One, 21(11), e0362851. https://doi.org/10.1371/journal.pone.0362851
Vancouver
O'Brien TE, Silcox JW. Beyond the basics: Using nonlinear approaches to classical statistical tests to improve fit and interpretability. PLOS One. 2026;21(11):e0362851. doi:10.1371/journal.pone.0362851
BibTeX
@article{OBrien2026,
author = {O'Brien, Timothy E and Silcox, Jack W},
title = {Beyond the basics: Using nonlinear approaches to classical statistical tests to improve fit and interpretability},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {11},
pages = {e0362851},
doi = {10.1371/journal.pone.0362851}
}
EUVIMED