Saddlepoint approximation in exponential models with boundary points
Del Castillo, Joan ; López-Ratera, Anna
Bernoulli, Tome 12 (2006) no. 2, p. 491-500 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
A saddlepoint approximation is developed for the likelihood ratio test statistic in non-regular exponential models. For the one-parameter case, it is proved that the saddlepoint correction has a relative error of order [math] , assuming that the canonical statistic has four finite moments. The results are applied in reliability theory and survival analysis, testing for exponentiality. Note that we are using the saddlepoint method for statistics without moment generating function.
Publié le : 2006-06-14
Classification:  higher-order asymptotics,  likelihood ratio test,  reliability theory,  survival analysis models 
@article{1151525132,
     author = {Del Castillo, Joan and L\'opez-Ratera, Anna},
     title = {Saddlepoint approximation in exponential models with boundary points},
     journal = {Bernoulli},
     volume = {12},
     number = {2},
     year = {2006},
     pages = { 491-500},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1151525132}
}

Del Castillo, Joan; López-Ratera, Anna. Saddlepoint approximation in exponential models with boundary points. Bernoulli, Tome 12 (2006) no. 2, pp.  491-500. http://gdmltest.u-ga.fr/item/1151525132/