Clustering data with values missing at random using scale mixtures of multivariate skew-normal distributions

Handling missing data is a major challenge in model-based clustering, especially when the data exhibit skewness and heavy tails. We address this by extending the finite mixture of scale mixtures of multivariate skew-normal (FMSMSN) family to accommodate incomplete data under a missing at random (MAR) mechanism. Unlike previous work that is limited to one of the special cases of the FMSMSN family, our method offers a cluster analysis methodology for the entire family that accounts for skewness and excess kurtosis amidst data with missing values. The multivariate skew-normal distribution, as parameterised by \cite{azzalini1996} and \cite{arnoldbeaver} includes the normal distribution as a special case, which ensures that our method is flexible toward existing symmetric model-based clustering techniques under a normality assumption. We derive the distributional properties of the missing components of the data and propose an augmented EM-type algorithm tailored for incomplete observations. The modified E-step yields closed-form expressions for the conditional expectations of the missing values. The simulation experiments showcase the flexibility of the FMSMSN family in both clustering performance and parameter recovery for varying percentages of missing values, while incorporating the effects of sample size and cluster proximity. Finally, we illustrate the practical utility of the proposed method by applying special cases of the FMSMSN family to global CO2 emissions data.

• Publication year

  2025

• Venue

  Unknown venue

• Publication date

  2025-07-27

• Fields of study

  Mathematics

• Identifiers
  arXiv 2507.20329
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Unmasking climate vulnerability in Africa: the role of CO2 and CH4 emissions on rising temperatures and sea levels

  2025cited by this paper
• Finite mixture of regression models for censored data based on the skew-t distribution

  2024cited by this paper
• Decomposition Analysis of CO2 Emissions in 138 Countries During the COVID-19 Pandemic

  2024cited by this paper
• Scale mixtures of multivariate centered skew-normal distributions

  2024cited by this paper
• Noise Filtering Algorithm Using Gaussian Mixture Models for High-Resolution Mass Spectra of Natural Organic Matter.

  2024cited by this paper
• Missing Values and Directional Outlier Detection in Model-Based Clustering

  2023cited by this paper
• ANALYSIS AND PROJECTIONS OF CARBON DIOXIDE (CO2) EMISSIONS IN THE US, EU, AND CHINA: A COMPARATIVE STUDY

  2023cited by this paper
• Likelihood-based inference for the multivariate skew-t regression with censored or missing responses

  2023cited by this paper
• Model-based clustering and outlier detection with missing data

  2022cited by this paper
• A Comparison of Three Popular Methods for Handling Missing Data: Complete-Case Analysis, Inverse Probability Weighting, and Multiple Imputation

  2022cited by this paper
• The skew-t censored regression model: parameter estimation via an EM-type algorithm

  2022cited by this paper
• An EM algorithm for estimating the parameters of the multivariate skew-normal distribution with censored responses

  2022cited by this paper
• Export quality, economic growth, and renewable-nonrenewable energy use: non-linear evidence through regime shifts

  2022cited by this paper
• The Impact of Covid-19 Pandemic on Stock Market Return Volatility: Evidence from Malaysia and Singapore

  2021cited by this paper
• Energy use, economic growth and CO2 emissions in Africa: does the environmental Kuznets curve hypothesis exist? New evidence from heterogeneous panel under cross-sectional dependence

  2021cited by this paper
• Dynamic linkages between non-renewable energy, renewable energy and economic growth through nonlinear ARDL approach: evidence from Malaysia

  2021cited by this paper
• Canonical fundamental skew-t linear mixed models

  2021cited by this paper
• Earthquake Phase Association Using a Bayesian Gaussian Mixture Model

  2021cited by this paper
• A Multivariate Flexible Skew-Symmetric-Normal Distribution: Scale-Shape Mixtures and Parameter Estimation via Selection Representation

  2021cited by this paper
• Strategies and scenarios to reduce energy consumption and CO2 emission in the urban, rural and sustainable neighbourhoods

  2021cited by this paper
• Missing Data in Prediction Research: A Five-Step Approach for Multiple Imputation, Illustrated in the CENTER-TBI Study

  2021cited by this paper
• Particle Size Distributions for Cellulose Nanocrystals Measured by Transmission Electron Microscopy: An Interlaboratory Comparison.

  2020cited by this paper
• Imputed spatial data: Cautions arising from response and covariate imputation measurement error

  2020cited by this paper
• Quantum-Assisted Measurement of Atomic Diamagnetism

  2020cited by this paper
• Generation of energy and environmental-economic growth consequences: Is there any difference across transition economies?

  2020cited by this paper
• Finite mixture modeling of censored and missing data using the multivariate skew-normal distribution

  2020cited by this paper
• A Bayesian multivariate mixture model for skewed longitudinal data with intermittent missing observations: An application to infant motor development

  2020cited by this paper
• Learning grain boundary segregation energy spectra in polycrystals

  2020cited by this paper
• Gaussian mixture model with feature selection: An embedded approach

  2020cited by this paper
• Web Appendix for: Robust model-based clustering with mild and gross outliers

  2019cited by this paper
• Model-Based Clustering and Classification Using Mixtures of Multivariate Skewed Power Exponential Distributions

  2019cited by this paper
• Impact of missing data on bias and precision when estimating change in patient-reported outcomes from a clinical registry

  2019cited by this paper
• Modelling carbon emission intensity: Application of artificial neural network

  2019cited by this paper
• Robust finite mixture modeling of multivariate unrestricted skew-normal generalized hyperbolic distributions

  2018cited by this paper
• Likelihood-based inference for multivariate skew scale mixtures of normal distributions

  2016cited by this paper
• An ECM algorithm for Skewed Multivariate Variance Gamma Distribution in Normal Mean-Variance Representation

  2015cited by this paper
• Multivariate Skew-Normal Generalized Hyperbolic distribution and its properties

  2014cited by this paper
• What Is Meant by "Missing at Random"?

  2013cited by this paper
• Parsimonious skew mixture models for model-based clustering and classification

  2013cited by this paper
• Mixtures of Variance-Gamma Distributions

  2013cited by this paper
• Multivariate mixture modeling using skew-normal independent distributions

  2012cited by this paper
• Initializing the EM algorithm in Gaussian mixture models with an unknown number of components

  2012cited by this paper
• Multivariate measurement error models based on scale mixtures of the skew–normal distribution

  2010cited by this paper
• Statistical applications of the multivariate skew normal distribution

  2009cited by this paper
• Numerical Recipes 3rd Edition: The Art of Scientific Computing

  2007cited by this paper
• Multivariate skew-normal distributions with applications in insurance

  2006cited by this paper
• On the multivariate Skew-Normal distribution and its scale mixtures

  2005cited by this paper
• A multivariate skew normal distribution

  2004cited by this paper
• A class of multivariate skew-normal models

  2004cited by this paper
• A new class of multivariate skew distributions with applications to bayesian regression models

  2003cited by this paper
• Skewed multivariate models related to hidden truncation and/or selective reporting

  2002cited by this paper
• A note on parameter estimation in the multivariate beta distribution

  1992cited by this paper

• Sleep pattern profiling using a finite mixture of contaminated multivariate skew-normal distributions on incomplete data

  2025cites this paper