Coherent Statistical Inference and Bayes Theorem
Berti, Patrizia ; Regazzini, Eugenio ; Rigo, Pietro
Ann. Statist., Tome 19 (1991) no. 1, p. 366-381 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
Conditions are given which suffice for the assessment of a coherent inference by means of a Bayesian algorithm, i.e., a suitable extension of the classical Bayes theorem relative to a finite number of alternatives. Under some further hypotheses such inference is shown to be, in addition, coherent in the sense of Heath, Lane and Sudderth. Moreover, a characterization of coherent posteriors is provided, together with some remarks concerning finitely additive conditional probabilities.
Publié le : 1991-03-14
Classification:  Bayes theorem,  coherent conditional probability,  conglomerability,  coherent posterior,  disintegrability,  integration with respect to a finitely additive set function,  62A15,  60A05 
@article{1176347988,
     author = {Berti, Patrizia and Regazzini, Eugenio and Rigo, Pietro},
     title = {Coherent Statistical Inference and Bayes Theorem},
     journal = {Ann. Statist.},
     volume = {19},
     number = {1},
     year = {1991},
     pages = { 366-381},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176347988}
}

Berti, Patrizia; Regazzini, Eugenio; Rigo, Pietro. Coherent Statistical Inference and Bayes Theorem. Ann. Statist., Tome 19 (1991) no. 1, pp.  366-381. http://gdmltest.u-ga.fr/item/1176347988/