HolaA fully sequential approach to the estimation of the difference of two population means for distributions belonging to the exponential family of distributions is adopted and compared with the best fixed design. Results on the lower bound for the Bayes risk due to estimation and expected cost are presented and shown to be of first order efficiency.
Applications involving the Poisson and exponential distributions with gamma priors as well as the Bernoulli distribution with beta priors are given. Finally, some numerical results are presented.
MSC: 62L12 Keywords: Estimation, Loss function, Prior distribution, Sequential design HolaAdoptem un plantejament complet i exhaustiu per estudiar les difer`encies entre les mitjanes poblacionals per a distribucions de la fam¿ýlia exponencial, que comparem amb el millor disseny d¿efectes fixs. Presentem resultats sobre la cota inferior del risc de Bayes lligat a l¿estimaci¿o i provem la seva efici`encia de primer ordre. Donem aplicacions implicant les distribucions de Poisson i exponencial amb priors gammas aix¿ý com la distribuci¿o de Bernoulli amb priors beta. Finalment, presentem alguns resultats num`erics.
Paraules clau: estimaci¿o, funci¿o de p`erdua, distribuci¿o prior, disseny seq¿uencial
© 2001-2024 Fundación Dialnet · Todos los derechos reservados