Estimation and prediction using belief functions: Application to stochastic frontier analysis

© Springer International Publishing Switzerland 2015. We outline an approach to statistical inference based on belief functions. For estimation, a consonant belief functions is constructed from the likelihood function. For prediction, the method is based on an equation linking the unobserved random...

Full description

Saved in:
Bibliographic Details
Main Authors: Kanjanatarakul,O., Kaewsompong,N., Sriboonchitta,S., Denœux,T.
Format: Article
Published: Springer Verlag 2015
Subjects:
Online Access:http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84919344191&origin=inward
http://cmuir.cmu.ac.th/handle/6653943832/39143
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-39143
record_format dspace
spelling th-cmuir.6653943832-391432015-06-16T08:07:45Z Estimation and prediction using belief functions: Application to stochastic frontier analysis Kanjanatarakul,O. Kaewsompong,N. Sriboonchitta,S. Denœux,T. Artificial Intelligence © Springer International Publishing Switzerland 2015. We outline an approach to statistical inference based on belief functions. For estimation, a consonant belief functions is constructed from the likelihood function. For prediction, the method is based on an equation linking the unobserved random quantity to be predicted, to the parameter and some underlying auxiliary variable with known distribution. The approach allows us to compute a predictive belief function that reflects both estimation and random uncertainties. Themethod is invariant to one-to-one transformations of the parameter and compatible with Bayesian inference, in the sense that it yields the same results when provided with the same information. It does not, however, require the user to provide prior probability distributions. The method is applied to stochastic frontier analysis with cross-sectional data. We demonstrate how predictive belief functions on inefficiencies can be constructed for this problem and used to assess the plausibility of various assertions. 2015-06-16T08:07:44Z 2015-06-16T08:07:44Z 2015-01-01 Article 1860949X 2-s2.0-84919344191 10.1007/978-3-319-13449-9_12 http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84919344191&origin=inward http://cmuir.cmu.ac.th/handle/6653943832/39143 Springer Verlag
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
topic Artificial Intelligence
spellingShingle Artificial Intelligence
Kanjanatarakul,O.
Kaewsompong,N.
Sriboonchitta,S.
Denœux,T.
Estimation and prediction using belief functions: Application to stochastic frontier analysis
description © Springer International Publishing Switzerland 2015. We outline an approach to statistical inference based on belief functions. For estimation, a consonant belief functions is constructed from the likelihood function. For prediction, the method is based on an equation linking the unobserved random quantity to be predicted, to the parameter and some underlying auxiliary variable with known distribution. The approach allows us to compute a predictive belief function that reflects both estimation and random uncertainties. Themethod is invariant to one-to-one transformations of the parameter and compatible with Bayesian inference, in the sense that it yields the same results when provided with the same information. It does not, however, require the user to provide prior probability distributions. The method is applied to stochastic frontier analysis with cross-sectional data. We demonstrate how predictive belief functions on inefficiencies can be constructed for this problem and used to assess the plausibility of various assertions.
format Article
author Kanjanatarakul,O.
Kaewsompong,N.
Sriboonchitta,S.
Denœux,T.
author_facet Kanjanatarakul,O.
Kaewsompong,N.
Sriboonchitta,S.
Denœux,T.
author_sort Kanjanatarakul,O.
title Estimation and prediction using belief functions: Application to stochastic frontier analysis
title_short Estimation and prediction using belief functions: Application to stochastic frontier analysis
title_full Estimation and prediction using belief functions: Application to stochastic frontier analysis
title_fullStr Estimation and prediction using belief functions: Application to stochastic frontier analysis
title_full_unstemmed Estimation and prediction using belief functions: Application to stochastic frontier analysis
title_sort estimation and prediction using belief functions: application to stochastic frontier analysis
publisher Springer Verlag
publishDate 2015
url http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84919344191&origin=inward
http://cmuir.cmu.ac.th/handle/6653943832/39143
_version_ 1681421601157939200