Berekening van a posteriori-verdeling in Bayes-analise: toepassing in ’n betroubaarheidstelsel wat afwisselend gebruik word
Suid-Afrikaanse Tydskrif vir Natuurwetenskap en Tegnologie/South African Journal of Science and Technology
| Field | Value | |
| Title | Berekening van a posteriori-verdeling in Bayes-analise: toepassing in ’n betroubaarheidstelsel wat afwisselend gebruik word Computation of posterior distribution in Bayesian analysis – application in an intermittently used reliability system | |
| Creator | Yadavalli, V. S.S. Mostert, P. J. Bekker, A. Botha, M. | |
| Description | Die Bayes-beraming van die stasionêre tempo van teleurstellings, D∞, vir twee modelle (met verskillende spesifikasies) van stelsels wat afwisselend gebruik word, word voorgestel. Daar word veronderstel dat die stogastiese veranderlikes van die stelsel onafhanklik eksponensiaal verdeel is. Jeffrey se a priori-verdeling word vir die onbekende parameters aanvaar. Die komplekse en nieliniêre definisie van D∞ beperk inferensie in albei modelle. Monte Carlo-simulasie word gebruik om die a posteriori-verdeling van D∞ en daarna die hoogste a posteriori-digtheidsintervalle (HPD) af te lei. ’n Numeriese voorbeeld waarin Bayes-beramers en die HPD-intervalle bereken word, illustreer hierdie resultate. Die frekwentistiese eienskappe van hierdie Bayes-prosedure word bepaal deur oordekkingsproporsies te bereken vir elk van hierdie HPD-intervalle vir vaste waardes van die parameters. Bayesian estimation is presented for the stationary rate of disappointments, D∞, for two models (with different specifications) of intermittently used systems. The random variables in the system are considered to be independently exponentially distributed. Jeffreys’ prior is assumed for the unknown parameters in the system. Inference about D∞ is being restrained in both models by the complex and non-linear definition of D∞. Monte Carlo simulation is used to derive the posterior distribution of D∞ and subsequently the highest posterior density (HPD) intervals. A numerical example where Bayes estimates and the HPD intervals are determined illustrates these results. This illustration is extended to determine the frequentistical properties of this Bayes procedure, by calculating covering proportions for each of these HPD intervals, assuming fixed values for the parameters. | |
| Publisher | AOSIS | |
| Date | 2002-09-28 | |
| Identifier | 10.4102/satnt.v21i3.231 | |
| Source | Suid-Afrikaanse Tydskrif vir Natuurwetenskap en Tegnologie; Vol 21, No 3 (2002); 78-82 Suid-Afrikaanse Tydskrif vir Natuurwetenskap en Tegnologie; Vol 21, No 3 (2002); 78-82 2222-4173 0254-3486 | |
| Language | eng | |
| Relation |
The following web links (URLs) may trigger a file download or direct you to an alternative webpage to gain access to a publication file format of the published article:
https://journals.satnt.aosis.co.za/index.php/satnt/article/view/231/219
|
|
ADVERTISEMENT
