Why the Decision-Theoretic Perspective Misrepresents Frequentist Inference: Revisiting Stein's Paradox and Admissibility

Aris Spanos

A chapter in Advances in Statistical Methodologies and Their Application to Real Problems from IntechOpen

Abstract: The primary objective of this paper is to make a case that R.A. Fisher's objections to the decision-theoretic framing of frequentist inference are not without merit. It is argued that this framing is congruent with the Bayesian but incongruent with the frequentist approach; it provides the former with a theory of optimal inference but misrepresents the optimality theory of the latter. Decision-theoretic and Bayesian rules are considered optimal when they minimize the expected loss "for all possible values of ? in ?" [????], irrespective of what the true value ?* [state of Nature] happens to be; the value that gave rise to the data. In contrast, the theory of optimal frequentist inference is framed entirely in terms of the capacity of the procedure to pinpoint ?*. The inappropriateness of the quantifier ???? calls into question the relevance of admissibility as a minimal property for frequentist estimators. As a result, the pertinence of Stein's paradox, as it relates to the capacity of frequentist estimators to pinpoint ?*, needs to be reassessed. The paper also contrasts loss-based errors with traditional frequentist errors, arguing that the former are attached to ?, but the latter to the inference procedure itself.

Keywords: decision theoretic inference; Bayesian vs. frequentist inference; Stein's paradox; James-Stein estimator; loss functions; admissibility; error probabilities; loss functions; risk functions; complete class theorem (search for similar items in EconPapers)
JEL-codes: C60 (search for similar items in EconPapers)
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.intechopen.com/chapters/54796 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ito:pchaps:107718

DOI: 10.5772/65720

Access Statistics for this chapter

More chapters in Chapters from IntechOpen
Bibliographic data for series maintained by Slobodan Momcilovic (ai@intechopen.com).