Normal view MARC view

Inference with imperfect sampling from a Bernoulli process

Author: Gaba, Anil ; Winkler, Robert L.INSEAD Area: Technology and Operations Management In: Bayesian and likelihood methods in statistics and econometrics:essays in honor of George A. Barnard - Barnard, George A.;Geisser, Seymour - 1990 - Book Language: EnglishDescription: p. 303-317.Type of document: INSEAD ChapterNote: Please ask the Library for this chapter.Abstract: When a sample is taken from a dichotomous process, various sources of noise may cause some observvations to be classified incorrectly. In this paper, imperfect sampling from a Bernoulli process with a noise parameter that is not known is considered. A likelihood analysis reveals an identification problem, which is avoided under a Bayesian analysis with a joint prior distribution on the noise parameter to illustrate the methodology and to provide some flavour of the implications of the noise and uncertainty about the noise for inferences about a proportion.
Tags: No tags from this library for this title. Add tag(s)
Log in to add tags.
Item type Current location Collection Call number Status Date due
INSEAD Chapter Digital Library
PDF Available

Please ask the Library for this chapter.

When a sample is taken from a dichotomous process, various sources of noise may cause some observvations to be classified incorrectly. In this paper, imperfect sampling from a Bernoulli process with a noise parameter that is not known is considered. A likelihood analysis reveals an identification problem, which is avoided under a Bayesian analysis with a joint prior distribution on the noise parameter to illustrate the methodology and to provide some flavour of the implications of the noise and uncertainty about the noise for inferences about a proportion.

Digitized

There are no comments for this item.

Log in to your account to post a comment.
Koha 3.18 - INSEAD Library Catalogue
Library Home | Contact Us | What's Koha?