Local mixture models of exponential families

DOI10.3150/07-BEJ6170MaRDI QIDQ2469644zbMATH OpenOpenAlexFDO

Authors Karim Anaya-Izquierdo, Paul Marriott

Publication date 6 February 2008

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0709.0447, https://projecteuclid.org/euclid.bj/1186503479

zbMATH Keywords

affine geometryconvex geometrydifferential geometrydispersion modelstatistical manifold

Mathematics Subject Classification ID

Local differential geometry (53B99) Foundations and philosophical topics in statistics (62A01) Characterization and structure theory of statistical distributions (62E10)

Abstract: Exponential families are the workhorses of parametric modelling theory. One reason for their popularity is their associated inference theory, which is very clean, both from a theoretical and a computational point of view. One way in which this set of tools can be enriched in a natural and interpretable way is through mixing. This paper develops and applies the idea of local mixture modelling to exponential families. It shows that the highly interpretable and flexible models which result have enough structure to retain the attractive inferential properties of exponential families. In particular, results on identification, parameter orthogonality and log-concavity of the likelihood are proved.

Recommendations

• Local mixtures of the exponential distribution
• Exponential family mixture models (with least-squares estimators)
• On the local geometry of mixture models
• Extending local mixture models
• Mixture models: building a parameter space

Cites work

• Asymptotic approximations of integrals
• Data-informed influence analysis
• Differential-geometrical methods in statistics
• scientific article; zbMATH DE number 3692432 (Why is no real title available?)
• scientific article; zbMATH DE number 1253515 (Why is no real title available?)
• scientific article; zbMATH DE number 1860211 (Why is no real title available?)
• scientific article; zbMATH DE number 3219970 (Why is no real title available?)
• Local mixtures of the exponential distribution
• Natural exponential families with quadratic variance functions
• Natural exponential families with quadratic variance functions: Statistical theory
• Natural real exponential families with cubic variance functions
• On the efficiency of quasi-likelihood estimation
• On the geometry of measurement error models
• On the local geometry of mixture models
• Quasi-likelihood functions
• Sharp inequalities between skewness and kurtosis for unimodal distributions
• Some remarks on overdispersion

Cited in

(18)

• A connection between the double gamma model and Laplace sample mean
• Exponential family mixture models (with least-squares estimators)
• Local score tests in mixture exponential family
• Simplification and hierarchical representations of mixtures of exponential families
• Global-local mixtures: a unifying framework
• Mixture models: building a parameter space
• Computing boundaries in local mixture models
• New results on mixture and exponential models by Orlicz spaces
• Semiparametric Mixtures of Generalized Exponential Families
• scientific article; zbMATH DE number 1304656 (Why is no real title available?)
• Exponential mixtures and quadratic exponential families
• On the local geometry of mixture models
• Mixture decompositions of exponential families using a decomposition of their sample spaces
• Generalising frailty assumptions in survival analysis: a geometric approach
• Localized mixture models for prediction with application
• Moment ideals of local Dirac mixtures
• Extending local mixture models
• Local mixtures of the exponential distribution

This page was built for publication: Local mixture models of exponential families

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2469644)