國立高雄大學圖資館 |

Language: English

Back

Belief functions applied to reliability testing and product improvement

Record Type:	Electronic resources : Monograph/item
Title/Author:	Belief functions applied to reliability testing and product improvement
Author:	Chiu, Wai Fung.
Description:	67 p.
Notes:	Adviser: Arthur P. Dempster.
Notes:	Source: Dissertation Abstracts International, Volume: 65-05, Section: B, page: 2469.
Contained By:	Dissertation Abstracts International65-05B.
Subject:	Statistics.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3131809
ISBN:	0496790498

Belief functions applied to reliability testing and product improvement
Chiu, Wai Fung.

Belief functions applied to reliability testing and product improvement [electronic resource] - 67 p.

Adviser: Arthur P. Dempster.

Thesis (Ph.D.)--Harvard University, 2004.

We define and illustrate an approach to reliability testing and product improvement that allows extension of the familiar Bayesian methodology to the more inclusive Dempster-Shafer (DS) belief function logic. The product development process considered here consists of a sequence of test-analyze-and-fix stages. In each stage, similar copies of the product are tested, test results are analyzed, and knowledge gained from the analysis is translated into modifications aimed at fixing the product to achieve higher reliability. It is assumed that the test results are binomial data, and that the modifications improve product reliability. Whereas the Bayesian special case requires input of a probability distribution representing the degree of improvement achieved at the end of each stage, the DS method permits a weaker form of expert input concerning improvement, through a collection of belief functions that includes a full Bayesian prior at one extreme and a statement of complete ignorance at the other. Reliability assessment at any stage combines past and current test data with past and current expert inputs, where the combination process makes use of simple and efficient numerical algorithms that take advantage of the underlying join-tree structure associated with hidden Markov models.

ISBN: 0496790498Subjects--Topical Terms:

182057
Statistics.

Belief functions applied to reliability testing and product improvement
LDR:02296nmm _2200277 _450 001 162679
005 20051017073511.5
008 230606s2004 eng d
020 $a 0496790498
035 $a 00149180
035 $a 162679
040 $a UnM $c UnM
100 0 $a Chiu, Wai Fung. $3 227823
245 1 0 $a Belief functions applied to reliability testing and product improvement $h [electronic resource]
300 $a 67 p.
500 $a Adviser: Arthur P. Dempster.
500 $a Source: Dissertation Abstracts International, Volume: 65-05, Section: B, page: 2469.
502 $a Thesis (Ph.D.)--Harvard University, 2004.
520 # $a We define and illustrate an approach to reliability testing and product improvement that allows extension of the familiar Bayesian methodology to the more inclusive Dempster-Shafer (DS) belief function logic. The product development process considered here consists of a sequence of test-analyze-and-fix stages. In each stage, similar copies of the product are tested, test results are analyzed, and knowledge gained from the analysis is translated into modifications aimed at fixing the product to achieve higher reliability. It is assumed that the test results are binomial data, and that the modifications improve product reliability. Whereas the Bayesian special case requires input of a probability distribution representing the degree of improvement achieved at the end of each stage, the DS method permits a weaker form of expert input concerning improvement, through a collection of belief functions that includes a full Bayesian prior at one extreme and a statement of complete ignorance at the other. Reliability assessment at any stage combines past and current test data with past and current expert inputs, where the combination process makes use of simple and efficient numerical algorithms that take advantage of the underlying join-tree structure associated with hidden Markov models.
590 $a School code: 0084.
650 # 0 $a Statistics. $3 182057
650 # 0 $a Operations Research. $3 227148
690 $a 0463
690 $a 0796
710 0 # $a Harvard University. $3 212445
773 0 # $g 65-05B. $t Dissertation Abstracts International
790 $a 0084
790 1 0 $a Dempster, Arthur P., $e advisor
791 $a Ph.D.
792 $a 2004
856 4 0 $u http://libsw.nuk.edu.tw/login?url=http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3131809 $z http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3131809