A bayesian procedure in the context of sequential mastery testing

Fuente: Redalyc
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Hans J. Vos
Format: Artículo científico
Sprache:en
Veröffentlicht: Universitat de València 2000
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1876488034645442560
author Hans J. Vos
author_facet Hans J. Vos
contents A bayesian procedure in the context of sequential mastery testing Hans J. Vos Psicología threshold loss binomial distribution most efficient strategy Bayesian sequential rules sequential mastery testing The purpose of this paper is to derive optimal rules for sequential masterytests. In a sequential mastery test, the decision is to classify a subject as amaster, a nonmaster, or continuing testing and administering anotherrandom item. The framework of Bayesian sequential decision theory isused; that is, optimal rules are obtained by minimizing the posteriorexpected losses associated with all possible decision rules at each stage oftesting. The main advantage of this approach is that costs of testing can betaken explicitly into account. The binomial model is assumed for theprobability of a correct response given the true level of functioning,whereas threshold loss is adopted for the loss function involved. The paperconcludes with a simulation study, in which the Bayesian sequentialstrategy is compared with other procedures that exist for similarclassification decision problems in the literature. 2000 artículo científico 0211-2159 https://www.redalyc.org/articulo.oa?id=16921111 en http://www.redalyc.org/revista.oa?id=169 Psicológica application/pdf Universitat de València Psicológica (España) Num.1 Vol.21
format Artículo científico
id redalyc_16921111
institution Redalyc
language en
publishDate 2000
publisher Universitat de València
spellingShingle A bayesian procedure in the context of sequential mastery testing
Hans J. Vos
Psicología
threshold loss
binomial distribution
most efficient strategy
Bayesian sequential rules
sequential mastery testing
A bayesian procedure in the context of sequential mastery testing Hans J. Vos Psicología threshold loss binomial distribution most efficient strategy Bayesian sequential rules sequential mastery testing The purpose of this paper is to derive optimal rules for sequential masterytests. In a sequential mastery test, the decision is to classify a subject as amaster, a nonmaster, or continuing testing and administering anotherrandom item. The framework of Bayesian sequential decision theory isused; that is, optimal rules are obtained by minimizing the posteriorexpected losses associated with all possible decision rules at each stage oftesting. The main advantage of this approach is that costs of testing can betaken explicitly into account. The binomial model is assumed for theprobability of a correct response given the true level of functioning,whereas threshold loss is adopted for the loss function involved. The paperconcludes with a simulation study, in which the Bayesian sequentialstrategy is compared with other procedures that exist for similarclassification decision problems in the literature. 2000 artículo científico 0211-2159 https://www.redalyc.org/articulo.oa?id=16921111 en http://www.redalyc.org/revista.oa?id=169 Psicológica application/pdf Universitat de València Psicológica (España) Num.1 Vol.21
title A bayesian procedure in the context of sequential mastery testing
topic Psicología
threshold loss
binomial distribution
most efficient strategy
Bayesian sequential rules
sequential mastery testing
url https://www.redalyc.org/articulo.oa?id=16921111