Robust statistical modelling using the multivariate skew t distribution with complete and incomplete data

DOI10.1177/1471082X1001100305zbMath1218.62050MaRDI QIDQ3019509

Tzy-Chy Lin, Tsung I. Lin

Publication date: 28 July 2011

Published in: Statistical Modelling (Search for Journal in Brave)

zbMATH Keywords

multiple imputationmissing at randomdata augmentationMCECM algorithmMST modelmultivariate truncated \(t\) distribution

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Estimation in multivariate analysis (62H12) Robustness and adaptive procedures (parametric inference) (62F35) Nonparametric tolerance and confidence regions (62G15) Monte Carlo methods (65C05)

Related Items (9)

Clustering with the multivariate normal inverse Gaussian distribution ⋮ Robust skew-\(t\) factor analysis models for handling missing data ⋮ A robust factor analysis model based on the canonical fundamental skew-\(t\) distribution ⋮ Maximum likelihood methods in a robust censored errors-in-variables model ⋮ Bayesian analysis of skew-normal independent linear mixed models with heterogeneity in the random-effects population ⋮ A robust factor analysis model using the restricted skew-\(t\) distribution ⋮ Mixtures of generalized hyperbolic distributions and mixtures of skew-\(t\) distributions for model-based clustering with incomplete data ⋮ Bayesian inference for the multivariate skew-normal model: a population Monte Carlo approach ⋮ Semiparametric inference for the scale-mixture of normal partial linear regression model with censored data

Uses Software

• SAS/STAT

Cites Work

• Random-Effects Models for Longitudinal Data
• Analysis of multivariate skew normal models with incomplete data
• Efficient ML estimation of the multivariate normal distribution from incomplete data
• Missing data imputation using the multivariate \(t\) distribution
• Supervised learning of multivariate skew normal mixture models with missing information
• Maximum likelihood estimation for multivariate skew normal mixture models
• Maximum likelihood estimation via the ECM algorithm: A general framework
• Robust Likelihood Methods Based on the Skew-t and Related Distributions
• Inference and missing data
• A new class of multivariate skew distributions with applications to bayesian regression models
• Distributions Generated by Perturbation of Symmetry with Emphasis on a Multivariate Skewt-Distribution
• Bayesian Measures of Model Complexity and Fit
• A Skew Extension of the T-Distribution, with Applications
• Multivariate T-Distributions and Their Applications
• Variance Components Testing in the Longitudinal Mixed Effects Model
• Monte Carlo sampling methods using Markov chains and their applications
• A comparison of Bayesian and likelihood-based methods for fitting multilevel models

This page was built for publication: Robust statistical modelling using the multivariate skew t distribution with complete and incomplete data