Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A Comparison of the Bayesian and Frequentist Approaches to EstimationThe Threshold Problem

A Comparison of the Bayesian and Frequentist Approaches to Estimation: The Threshold Problem [Both Bayesian and frequentist methods of inference have qualities which would seem to recommend them for use. They both also have apparent deficiencies. Both schools can find, without great difficulty, reasons to support the position they have chosen as well as reasons to critique the methodologies espoused by the other school. Many professional statisticians see themselves as being in one camp or the other but, in practice, remain open to using either of the methodologies when a particular application seems to call for them. A common example is a Bayesian’s use of the standard methods of linear model theory (regression analysis, for example), because the methodology is so well developed and easily interpretable; he might do so while, at the same time, being quite adamant about the use of the Bayesian approach to estimation and testing in other settings. Similarly, one often encounters staunch frequentists who are happy to use Bayesian methods on occasion (especially those labeled as “objective”) because of the enticing computational tools available for executing the Bayesian approach.] http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

A Comparison of the Bayesian and Frequentist Approaches to EstimationThe Threshold Problem

Part of the Springer Series in Statistics Book Series
Samaniego, Francisco J.
Springer Journals — May 28, 2010
Download PDF
15 pages

Loading next page...
 
/lp/springer-journals/a-comparison-of-the-bayesian-and-frequentist-approaches-to-estimation-oCmgXz0WA7
Publisher
Springer New York
Copyright
© Springer Science+Business Media, LLC 2010
ISBN
978-1-4419-5940-9
Pages
61 –76
DOI
10.1007/978-1-4419-5941-6_4
Publisher site
See Chapter on Publisher Site

Abstract

[Both Bayesian and frequentist methods of inference have qualities which would seem to recommend them for use. They both also have apparent deficiencies. Both schools can find, without great difficulty, reasons to support the position they have chosen as well as reasons to critique the methodologies espoused by the other school. Many professional statisticians see themselves as being in one camp or the other but, in practice, remain open to using either of the methodologies when a particular application seems to call for them. A common example is a Bayesian’s use of the standard methods of linear model theory (regression analysis, for example), because the methodology is so well developed and easily interpretable; he might do so while, at the same time, being quite adamant about the use of the Bayesian approach to estimation and testing in other settings. Similarly, one often encounters staunch frequentists who are happy to use Bayesian methods on occasion (especially those labeled as “objective”) because of the enticing computational tools available for executing the Bayesian approach.]

Published: May 28, 2010

Keywords: Prior Distribution; Bayesian Inference; Bayesian Approach; Frequentist Estimator; Exponential Family

There are no references for this article.