A 'Weight of Evidence' approach to evaluating structural equation models
One Ecosystem · 13.03.2020 · 5
DOI: 10.3897/oneeco.5.e50452 ↗Kurz gefasst
Fachartikel in der Zeitschrift One Ecosystem, online erschienen am 13.03.2020. Verfasst von James Grace. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 33 Literaturangaben.
Abstract (Originalsprache)
It is possible that model selection has been the most researched and most discussed topic in the history of both statistics and structural equation modeling (SEM). The reason for this is because selecting one model for interpretive use from amongst many possible models is both essential and difficult. The published protocols and advice for model evaluation and selection in SEM studies are complex and difficult to integrate with current approaches used in biology. Opposition to the use of p -values and decision thresholds has been voiced by the statistics community, yet certain phases of model evaluation have been historically tied to reliance on p -values. In this paper, I outline an approach to model evaluation, comparison and selection based on a weight-of-evidence paradigm. The details and proposed sequence of steps are illustrated using a real-world example. At the end of the paper, I briefly discuss the current state of knowledge and a possible direction for future studies.
Zitieren
APA
Grace, J. (2020). A 'Weight of Evidence' approach to evaluating structural equation models. One Ecosystem, 5. https://doi.org/10.3897/oneeco.5.e50452
Vancouver
Grace J. A 'Weight of Evidence' approach to evaluating structural equation models. One Ecosystem. 2020;5. doi:10.3897/oneeco.5.e50452
BibTeX
@article{Grace2020,
author = {Grace, James},
title = {A 'Weight of Evidence' approach to evaluating structural equation models},
journal = {One Ecosystem},
year = {2020},
volume = {5},
doi = {10.3897/oneeco.5.e50452}
}
EUVIMED