Full text not available from this repository.

Abstract

Recently, Veksler, Myers, and Gluck (2015) proposed model flexibility analysis as a method that “aidsmodel evaluation by providing a metric for gauging the persuasiveness of a given fit” (p. 755) Modelflexibility analysis measures the complexity of a model in terms of the proportion of all possible datapatterns it can predict. We show that this measure does not provide a reliable way to gauge complexity,which prevents model flexibility analysis from fulfilling either of the 2 aims outlined by Veksler et al.(2015): absolute and relative model evaluation. We also show that model flexibility analysis can even failto correctly quantify complexity in the most clear cut case, with nested models. We advocate for the useof well-established techniques with these characteristics, such as Bayes factors, normalized maximumlikelihood, or cross-validation, and against the use of model flexibility analysis. In the discussion, weexplore 2 issues relevant to the area of model evaluation: the completeness of current model selectionmethods and the philosophical debate of absolute versus relative model evaluation.

Item Type:	Article
Authors/Creators:	Evans, NJ and Howard, ZL and Heathcote, A and Brown, SD
Keywords:	Model Selection; Flexibility; Complexity; Goodness-of-fit
Journal or Publication Title:	Psychological Review
Publisher:	Amer Psychological Assoc
ISSN:	0033-295X
DOI / ID Number:	10.1037/rev0000057
Copyright Information:	© 2017 American Psychological Association
Related URLs:	Google Scholar: Heathcote, A UTAS Profile: Heathcote, A
Item Statistics:	View statistics for this item

Actions (login required)

Item Control Page