Saddlepoint approximation in exponential models with boundary points

Joan del Castillo, Anna López-Ratera

Research output: Contribution to journalArticleResearchpeer-review

6 Citations (Scopus)


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 O(n-1), 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. © 2006 ISI/BS.
Original languageEnglish
Pages (from-to)491-500
Publication statusPublished - 1 Jun 2006


  • Higher-order asymptotics
  • Likelihood ratio test
  • Reliability theory
  • Survival analysis models


Dive into the research topics of 'Saddlepoint approximation in exponential models with boundary points'. Together they form a unique fingerprint.

Cite this