Differential geometry, profile likelihood, L-sufficiency and composite transformation models

DOI10.1214/aos/1176350946zbMath0702.62032OpenAlexW2084540009WikidataQ115240724 ScholiaQ115240724MaRDI QIDQ915300

Ole Eiler Barndorff-Nielsen, Peter E. Jupp

Publication date: 1988

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aos/1176350946

zbMATH Keywords

integral representationmarginal likelihoodLaplace approximationprofile likelihoodtensorssubmersionstatistical manifoldsparameter of interestcutsorthogonal parametersalpha connectionscomposite transformation modelsdistributional shapeancillaryderivatives of pseudolikelihood functionsexpected information metricL-sufficient statisticobserved information metricprofile discrimination informationreproductive exponential modelstau- parallel foliations

Mathematics Subject Classification ID

Parametric inference (62F99) Local Riemannian geometry (53B20) Linear and affine connections (53B05) Sufficient statistics and fields (62B05) Methods of local Riemannian geometry (53B21)

Related Items (12)

Statistical manifolds with almost quaternionic structures and quaternionic Kähler-like statistical submersions ⋮ Composite transformation models: A fiducial perspective ⋮ Preferred point \(\alpha\)-manifold and Amari's \(\alpha\)-connections ⋮ Statistics, yokes and symplectic geometry ⋮ Approximations to most powerful invariant tests for multinormality against some irregular alternatives ⋮ Asymptotic properties of conditional maximum likelihood estimator in a certain exponential model ⋮ Statistical morphisms and related invariance properties ⋮ Tensors and likelihood expansions in the presence of nuisance parameters ⋮ An affine submersion with horizontal distribution and its applications ⋮ Unnamed Item ⋮ Affine and Conformal Submersions with Horizontal Distribution and Statistical Manifolds ⋮ Multivariate normal distributions parametrized as a Riemannian symmetric space

This page was built for publication: Differential geometry, profile likelihood, L-sufficiency and composite transformation models