The meta-inductivist's winning strategy in the prediction game: A new approach to Hume's problem

Philosophy of Science 75 (3):278-305 (2008)
Abstract
This article suggests a ‘best alternative' justification of induction (in the sense of Reichenbach) which is based on meta-induction . The meta-inductivist applies the principle of induction to all competing prediction methods which are accessible to her. It is demonstrated, and illustrated by computer simulations, that there exist meta-inductivistic prediction strategies whose success is approximately optimal among all accessible prediction methods in arbitrary possible worlds, and which dominate the success of every noninductive prediction strategy. The proposed justification of meta-induction is mathematically analytical. It implies, however, an a posteriori justification of object-induction based on the experiences in our world. *Received November 2005; revised March 2008. †To contact the author, please write to: Department of Philosophy, University of Duesseldorf, Universitaetsstrasse 1, Geb. 23.21, Duesseldorf, Germany D-40225; e-mail: gerhard.schurz@phil-fak.uni-duesseldorf.de.
Keywords No keywords specified (fix it)
Categories (categorize this paper)
DOI 10.1086/592550
Options
 Save to my reading list
Follow the author(s)
My bibliography
Export citation
Find it on Scholar
Edit this record
Mark as duplicate
Revision history
Request removal from index
Download options
Our Archive


Upload a copy of this paper     Check publisher's policy     Papers currently archived: 27,195
Through your library
References found in this work BETA
The Logic of Reliable Inquiry.Kevin Kelly - 1996 - Oxford University Press USA.
The Theory of Probability.Hans Reichenbach - 1949 - Berkeley: University of California Press.
Experience and Prediction.Hans Reichenbach - 1938 - University of Chicago Press.

View all 9 references / Add more references

Citations of this work BETA
How Much Evidence Should One Collect?Remco Heesen - 2015 - Philosophical Studies 172 (9):2299-2313.
What If the Principle of Induction Is Normative? Formal Learning Theory and Hume's Problem.Daniel Steel & S. Kedzie Hall - 2010 - International Studies in the Philosophy of Science 24 (2):171-185.

View all 10 citations / Add more citations

Similar books and articles

Monthly downloads

Added to index

2009-01-28

Total downloads

38 ( #134,777 of 2,163,984 )

Recent downloads (6 months)

1 ( #348,017 of 2,163,984 )

How can I increase my downloads?

My notes
Sign in to use this feature


Discussion
Order:
There  are no threads in this forum
Nothing in this forum yet.

Other forums