Maximum likelihood estimation of triangular and polygonal distributions

DOI10.1016/J.CSDA.2016.04.003MaRDI QIDQ1659022zbMATH OpenOpenAlexFDO

Authors Geoffrey J. McLachlan, Hien D. Nguyen

Publication date 15 August 2018

Published in Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1602.03692

zbMATH Keywords

mixture modelsminorization-maximization algorithmspolygonal distributionstriangular distributions

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08)

Abstract: Triangular distributions are a well-known class of distributions that are often used as elementary example of a probability model. In the past, enumeration and order statistic-based methods have been suggested for the maximum likelihood (ML) estimation of such distributions. A novel parametrization of triangular distributions is presented. The parametrization allows for the construction of an MM (minorization--maximization) algorithm for the ML estimation of triangular distributions. The algorithm is shown to both monotonically increase the likelihood evaluations, and be globally convergent. Using the parametrization is then applied to construct an MM algorithm for the ML estimation of polygonal distributions. This algorithm is shown to have the same numerical properties as that of the triangular distribution. Numerical simulation are provided to demonstrate the performances of the new algorithms against established enumeration and order statistics-based methods.

Recommendations

• Maximum likelihood estimation in convex hull models
• Maximum Likelihood Estimation for Nets of Conics
• Discrete triangular distributions and non-parametric estimation for probability mass function
• scientific article; zbMATH DE number 4044962
• Maximum likelihood characterization of distributions
• Maximum likelihood characterization of distributions
• Maximum likelihood estimation of dirichlet distributions
• Maximum likelihood estimation for Tukey's three corners

Cites work

• scientific article; zbMATH DE number 2164735 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• scientific article; zbMATH DE number 775283 (Why is no real title available?)
• A unified convergence analysis of block successive minimization methods for nonsmooth optimization
• An algorithm with guaranteed convergence for finding a zero of a function
• EM vs MM: a case study
• Finite mixture models
• Generalized trapezoidal distributions
• Laplace mixture of linear experts
• MM algorithms for generalized Bradley-Terry models.
• Maximum likelihood estimation of Gaussian mixture models without matrix operations
• Mixtures of spatial spline regressions for clustering and classification
• More maximum likelihood oddities
• Optimization
• Seamless R and C++ integration with Rcpp
• Spatial spline regression models
• Statistical distributions.
• The MM alternative to EM
• Variable selection using MM algorithms

Cited in

(5)

• Maximum Likelihood Estimation for Nets of Conics
• Some theoretical results regarding the polygonal distribution
• Risk analysis in practice and theory
• More maximum likelihood oddities
• Discrete triangular distributions and non-parametric estimation for probability mass function

Describes a project that uses

Uses Software

• Rcpp
• R

This page was built for publication: Maximum likelihood estimation of triangular and polygonal distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1659022)