Nonparametric estimation of the expected accumulated reward for semi-Markov chains

In this paper a nonparametric estimator of the expected value of a discounted semi-Markov reward chain is proposed. Its asymptotic properties are established and as a consequence of the asymptotic normality the confidence sets are obtained. An application in quality of life modelling is described.

Detalhes bibliográficos
Autor: D'Amico, Guglielmo
Tipo de documento: artigo
Data de publicação:2009
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2099/8948
Acesso em linha:https://hdl.handle.net/2099/8948
Access Level:Acceso aberto
Palavra-chave:Probabilities
Mathematical statistics
Discrete semi-Markov processes
Empirical estimators
Asymptotic properties
Quality of life
Probabilitats
Estadística matemàtica
Classificació AMS::60 Probability theory and stochastic processes::60K Special processes
Classificació AMS::62 Statistics::62M Inference from stochastic processes
Classificació AMS::62 Statistics::62G Nonparametric inference
Àrees temàtiques de la UPC::Matemàtiques i estadística::Estadística matemàtica
Descrição
Resumo:In this paper a nonparametric estimator of the expected value of a discounted semi-Markov reward chain is proposed. Its asymptotic properties are established and as a consequence of the asymptotic normality the confidence sets are obtained. An application in quality of life modelling is described.