Inherent Complexity: A Problem for Statistical Model Evaluation

Philosophy of Science 84 (5):797-809 (2017)
  Copy   BIBTEX

Abstract

This article investigates a problem for statistical model evaluation, in particular for curve fitting: by employing a different family of curves we can fit any scatter plot almost perfectly at apparently minor cost in terms of model complexity. The problem is resolved by an appeal to prior probabilities. This leads to some general lessons about how to approach model evaluation.

Other Versions

No versions found

Similar books and articles

Statistical Model Selection Criteria and the Philosophical Problem of Underdetermination.I. A. Kieseppä - 2001 - British Journal for the Philosophy of Science 52 (4):761-794.
Efficiency – Model for Scientific Research Evaluation.Panaite Nica & Silviu Mihail Tita - 2013 - Revista Romaneasca pentru Educatie Multidimensionala 5 (1):141-159.
Seeking a new biomedical model. How evolutionary biology may contribute.Stephen Lewis - 2009 - Journal of Evaluation in Clinical Practice 15 (4):745-748.

Analytics

Added to PP
2017-12-15

Downloads
125 (#367,069)

6 months
44 (#187,951)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Jan-Willem Romeijn
University of Groningen

Citations of this work

Variation 10: Simplicity and Model Selection.Jan Sprenger & Stephan Hartmann - 2019 - In Jan Sprenger & Stephan Hartmann, Bayesian Philosophy of Science. Oxford and New York: Oxford University Press. pp. 261-286.

Add more citations

References found in this work

No references found.

Add more references