Skip to Content
Decision Theory
book

Decision Theory

by Giovanni Parmigiani, Lurdes Inoue
May 2009
Intermediate to advanced
404 pages
11h 10m
English
Wiley
Content preview from Decision Theory

9Shrinkage

In this chapter we present a famous result due to Stein (1955) and further elaborated by James & Stein (1961). It concerns estimating several parameters as part of the same decision problem. Let x = (x1, ..., xp)′ be distributed according to a multivariate p-dimensional N(θ, I) distribution, and assume the multivariate quadratic loss function

Image

The estimator δ(x) = x is the maximum likelihood estimator of θ, it is unbiased, and it has the smallest risk among all unbiased estimators. This would make it the almost perfect candidate from a frequentist angle. It is also the formal Bayes rule if one wishes to specify an improper flat prior on θ. However, Stein showed that such an estimator is not admissible. Oops.

Robert describes the aftermath as follows:

One of the major impacts of the Stein paradox is to signify the end of a “Golden Age” for classical statistics, since it shows that the quest for the best estimator, i.e., the unique minimax admissible estimator, is hopeless, unless one restricts the class of estimators to be considered or incorporates some prior information. ... its main consequence has been to reinforce the Bayesian–frequentist interface, by inducing frequentists to call for Bayesian techniques and Bayesians to robustify their estimators in terms of frequentist performances and prior uncertainty. (Robert 1994, p. 67)

Efron adds:

The implications for objective ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

AirBnbBlueOriginElectronic ArtsHomeDepotNasdaqRakutenTata Consultancy Services

QuotationMarkO’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
QuotationMarkI wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
QuotationMarkI’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
QuotationMarkI'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Mark W.
Embedded Software Engineer

You might also like

The Human Factor in AI-Based Decision-Making

The Human Factor in AI-Based Decision-Making

Philip Meissner, Christoph Keding
The Hidden Cost of AI-Assisted Creativity

The Hidden Cost of AI-Assisted Creativity

Léonard Boussioux, Anil Doshi, Oliver Hauser, Kartik Hosanagar
Theory and Methods of Statistics

Theory and Methods of Statistics

P.K. Bhattacharya, Prabir Burman

Publisher Resources

ISBN: 9780471496571Purchase book