On large deviations and choice of ancillary for \(p^*\) and \(r^*\)

DOI10.2307/3318531zbMath0894.62026OpenAlexW1994242070MaRDI QIDQ1385006

Andrew T. A. Wood, Ole Eiler Barndorff-Nielsen

Publication date: 10 September 1998

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.2307/3318531

zbMATH Keywords

saddlepoint approximationmaximum likelihood estimatorconditional densityrelative errorLaplace's approximationcurved exponential modelslikelihood ancillarymodified directed likelihoodtail-area approximation

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Large deviations (60F10)

Related Items (5)

Asymptotic normality with small relative errors of posterior probabilities of half-spaces ⋮ Asymptotics and the theory of inference ⋮ Higher-order asymptotic normality of approximations to the modified signed likelihood ratio statistic for regular models ⋮ Bartlett identities and large deviations in likelihood theory ⋮ Laplace approximations for hypergeometric functions with matrix argument

This page was built for publication: On large deviations and choice of ancillary for \(p^*\) and \(r^*\)