The problem of testing a sharp null hypothesis by a Bayesian procedure shows some controversial issues. Here this problem is faced in the framework of vague distributions through the concept of pseudodensity. It is shown that the paradoxical aspects can be easily overcome by posing the problem in a proper setting which avoids resorting to probability densities.
Vague distributions in Bayesian testing of a null hypothesis / Gilio, Angelo; Scozzafava, Romano. - In: METRON. - ISSN 0026-1424. - STAMPA. - XLIII:3-4(1985), pp. 167-174.
Vague distributions in Bayesian testing of a null hypothesis
GILIO, ANGELO;SCOZZAFAVA, Romano
1985
Abstract
The problem of testing a sharp null hypothesis by a Bayesian procedure shows some controversial issues. Here this problem is faced in the framework of vague distributions through the concept of pseudodensity. It is shown that the paradoxical aspects can be easily overcome by posing the problem in a proper setting which avoids resorting to probability densities.File allegati a questo prodotto
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.