Journal Article

Prediction Versus Accommodation and the Risk of Overfitting

Christopher Hitchcock and Elliott Sober

in The British Journal for the Philosophy of Science

Published on behalf of British Society for the Philosophy of Science

Volume 55, issue 1, pages 1-34
Published in print March 2004 | ISSN: 0007-0882
Published online March 2004 | e-ISSN: 1464-3537 | DOI:
Prediction Versus Accommodation and the Risk of Overfitting

More Like This

Show all results sharing these subjects:

  • Philosophy of Science
  • Science and Mathematics


Show Summary Details


When a scientist uses an observation to formulate a theory, it is no surprise that the resulting theory accurately captures that observation. However, when the theory makes a novel prediction—when it predicts an observation that was not used in its formulation—this seems to provide more substantial confirmation of the theory. This paper presents a new approach to the vexed problem of understanding the epistemic difference between prediction and accommodation. In fact, there are several problems that need to be disentangled; in all of them, the key is the concept of overfitting. We float the hypothesis that accommodation is a defective methodology only when the methods used to accommodate the data fail to guard against the risk of overfitting. We connect our analysis with the proposals that other philosophers have made. We also discuss its bearing on the conflict between instrumentalism and scientific realism.


Predictivisms—a taxonomy


Formulating the problem

What might Annie be doing wrong?


Observations explained

Mayo on severe tests

The miracle argument and scientific realism

Concluding comments

Journal Article.  0 words. 

Subjects: Philosophy of Science ; Science and Mathematics

Full text: subscription required

How to subscribe Recommend to my Librarian

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.