Hitchcock and Sober on Weak Predictivism
Tóm tắt
According to Hitchcock and Sober’s argument from overfitting for weak predictivism, the fact that a theory accurately predicts a portion of its data is evidence that it has been formulated by balancing simplicity and goodness-of-fit rather than overfitting data. The core argument consists of two likelihood inequalities. In this paper I show that there is a surprising accommodation-friendly implication in their argument, and contend that it is beset by a substantial difficulty, namely, there is no good reason to think that their second likelihood inequality is true.
Tài liệu tham khảo
Barnes, E. (2008). The paradox of predictivism. Cambridge: Cambridge University Press.
Forster, M. (1995). The golfer’s dilemma: a reply to Kukla on curve-fitting. British Journal for the Philosophy of Science, 46, 348–60.
Forster, M., & Sober, E. (1994). How to tell when simpler, more unified, or less Ad Hoc theories will provide more accurate predictions. British Journal for the Philosophy of Science, 45, 1–35.
Hitchcock, C., & Sober, E. (2004). Prediction versus accommodation and the risk of overfitting. British Journal for the Philosophy of Science, 55, 1–34.
Horwich, P. (1982). Probability and evidence. Cambridge: Cambridge University Press.
Howson, C. (1988). Accommodation, prediction and bayesian confirmation theory. PSA, 1988, 381–392.
Kukla, A. (1995). Forster and sober on the curve-fitting problem. British Journal for the Philosophy of Science, 46, 248–52.
Popper, K. (1963). Conjectures and refutations. London: Routledge & Kegan Paul.
Sober, E. (2008). Evidence and evolution. Cambridge: Cambridge University Press.