0444111 20240103210100.920150528235959.9 000341466500030 84907360474 10.1016/j.ress.2014.04.015 7 s. P cav_un_epca*02548910951-83201311 (2014)291-297Elsevier Reliability analysis Goodness-of-fit Bayes statistics cav_un_auth*0101227 Volf Petr Stochastická informatika Department of Stochastic Informatics SI SI UTIA-B Department of Stochastic Informatics K 50 Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0257680 Timková Jana Stochastická informatika Department of Stochastic Informatics SI SI UTIA-B 50 Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2015/SI/volf-0444111.pdf This paper deals with the problem of proper lifetime model selection in the context of statistical reliability analysis. Namely, we consider regression models describing the dependence of failure intensities on a covariate, for instance a stressor. Testing the model fit is standardly based on the so-called martingale residuals. Their analysis has already been studied by many authors. Nevertheless, the Bayes approach to the problem is just developing. We shall present the Bayes procedure of stimation in several semi-parametric regression models of failure intensity. Then, our main concern is the Bayes construction of residual processes and goodness-of-fit tests basedon them. 2016 BB 2 RVO:67985556 http://hdl.handle.net/11104/0246859 S ENGINEERINGINDUSTRIAL|OPERATIONSRESEARCHMANAGEMENTSCIENCE 0.826 1.419 Q1 73.593 90.683 Q2 Q1 2014 84907360474 SCOPUS 000341466500030 WOS cav_un_epca*0254891 Reliability Engineering & System Safety 0951-8320 1879-0836 Roč. 131 č. 1 2014 291 297 Elsevier