A Constrained Optimization Framework
In this chapter I present arguments for the use of info-metrics as a fundamental framework for rational inference. The chapter consists of two interdependent parts. In the first I provide the framework for rational inference, which involves the use of a specific decision function to achieve the desired inference. In the second part I summarize four sets of axioms to justify the decision function argued for in the first part. All axioms lead to the same decision function: the entropy function of Boltzmann, Gibbs, and Shannon. In this chapter I emphasize underdetermined problems and problems of insufficient information, but I also discuss inference based on information resulting from repeated independent experiments. The same entropy function is identified in each case, as well as the desired decision function.
Oxford Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.
If you think you should have access to this title, please contact your librarian.