On testing the number of components in finite mixture models with known relevant component distributions

DOI10.2307/3315786zbMATH Open0911.62017OpenAlexW2001161033MaRDI QIDQ4378574FDOQ4378574

Authors: Jiahua Chen, Ping Cheng 

Publication date: 3 May 1999

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

Full work available at URL: https://doi.org/10.2307/3315786

Recommendations

• Generalized likelihood‐ratio test of the number of components in finite mixture models
• Publication:4892509
• Estimating the number of components in a finite mixture model: the special case of homogeneity

zbMATH Keywords

number of componentslocally most powerful testbootstrap log-likelihood-ratio

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Asymptotic properties of parametric tests (62F05)

Cites Work

• Statistical analysis of finite mixture distributions
• On the asymptotic accuracy of Efron's bootstrap
• The dip test of unimodality
• Title not available (Why is that?)
• Title not available (Why is that?)
• Asymptotic distribution of the likelihood ratio test that a mixture of two binomials is a single binomial

Cited In (9)

• Estimating the number of components in a finite mixture model: the special case of homogeneity
• Generalized likelihood‐ratio test of the number of components in finite mixture models
• Testing for a Finite Mixture Model with Two Components
• A combined likelihood ratio/information ratio bootstrap technique for estimating the number of components in finite mixtures
• Large sample distribution of the likelihood ratio test for normal mixtures
• Comparing approaches for testing the number of components in a finite mixture model
• Title not available (Why is that?)
• Hypothesis testing for finite mixture models
• On testing for the number of components in a mixed Poisson model

This page was built for publication: On testing the number of components in finite mixture models with known relevant component distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4378574)