Three Ways of Implementing the EM Algorithm when Parameters are not Identifiable

DOI<link itemprop=identifier href="https://doi.org/10.1002/1521-4036(200105)43:2<207::AID-BIMJ207>3.0.CO;2-H" /><207::AID-BIMJ207>3.0.CO;2-H 10.1002/1521-4036(200105)43:2<207::AID-BIMJ207>3.0.CO;2-HzbMath1152.62302OpenAlexW1998431274MaRDI QIDQ2748401

Jennifer So-Kuen Chan, Anthony Y. C. Kuk

Publication date: 14 October 2001

Full work available at URL: https://doi.org/10.1002/1521-4036(200105)43:2<207::aid-bimj207>3.0.co;2-h

zbMATH Keywords

Monte Carlo methodsIncomplete dataIdentifiability constraintsMultivariate order statistics modelsMultivariate probit regression

Mathematics Subject Classification ID

Statistics (62-XX) Monte Carlo methods (65C05)

Related Items (2)

Sequential Monte Carlo EM for multivariate probit models ⋮ Copula analysis of mixture models

Cites Work

• Normal Order Statistics as Permutation Probability Models

This page was built for publication: Three Ways of Implementing the EM Algorithm when Parameters are not Identifiable