Robust estimation of mixtures of regressions with random covariates, via trimming and constraints

A robust estimator for a wide family of mixtures of linear regression is presented. Robustness is based on the joint adoption of the cluster weighted model and of an estimator based on trimming and restrictions. The selected model provides the conditional distribution of the response for each group, as in mixtures of regression, and further supplies local distributions for the explanatory variables. A novel version of the restrictions has been devised, under this model, for separately controlling the two sources of variability identified in it. This proposal avoids singularities in the log-likelihood, caused by approximate local collinearity in the explanatory variables or local exact fits in regressions, and reduces the occurrence of spurious local maximizers. In a natural way, due to the interaction between the model and the estimator, the procedure is able to resist the harmful influence of bad leverage points along the estimation of the mixture of regressions, which is still an open issue in the literature. The given methodology defines a well-posed statistical problem, whose estimator exists and is consistent to the corresponding solution of the population optimum, under widely general conditions. A feasible EM algorithm has also been provided to obtain the corresponding estimation. Many simulated examples and two real datasets have been chosen to show the ability of the procedure, on the one hand, to detect anomalous data, and, on the other hand, to identify the real cluster regressions without the influence of contamination.

• Publication year

  2015

• Venue

  Statistics and computing

• Publication date

  2015-02-04

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1007/s11222-016-9628-3arXiv 1502.01118
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Robust Statistics

  2018influential reference
• The Generalized Linear Mixed Cluster-Weighted Model

  2015cited by this paper
• Robust mixture regression model fitting by Laplace distribution

  2014cited by this paper
• Avoiding spurious local maximizers in mixture modeling

  2014cited by this paper
• Robust Cluster Analysis and Variable Selection

  2014cited by this paper
• Robust mixture regression using the t-distribution

  2014influential reference
• A constrained robust proposal for mixture modeling avoiding spurious solutions

  2013cited by this paper
• A fast algorithm for robust constrained clustering

  2013cited by this paper
• Robust Mixture of Linear Regression Models

  2012influential reference
• Model-based clustering via linear cluster-weighted models

  2012cited by this paper
• Local Statistical Modeling via a Cluster-Weighted Approach with Elliptical Distributions

  2012influential reference
• Robust fitting of mixture regression models

  2012cited by this paper
• Exploring the number of groups in robust model-based clustering

  2011cited by this paper
• A weighted least-squares approach to clusterwise regression

  2011cited by this paper
• Constrained monotone EM algorithms for mixtures of multivariate t distributions

  2010cited by this paper
• A general trimming approach to robust Cluster Analysis

  2008influential reference
• FlexMix Version 2: Finite Mixtures with Concomitant Variables and Varying and Constant Parameters

  2008cited by this paper
• Finite Mixture Models

  2008cited by this paper
• Robust fitting of mixtures using the trimmed likelihood estimator

  2007influential reference
• Constrained monotone EM algorithms for finite mixture of multivariate Gaussians

  2007cited by this paper
• Robust Statistics

  2005cited by this paper
• of Classification 5 : 249-282 ( 1988 ) A Maximum Likelihood Methodology for Clusterwise Linear Regression

  2005influential reference
• Robust Regression and Outlier Detection

  2005influential reference
• Fixed Point Clusters for Linear Regression: Computation and Comparison

  2002influential reference
• Cluster-weighted modelling for time-series analysis

  1999cited by this paper
• A Fast Algorithm for the Minimum Covariance Determinant Estimator

  1999cited by this paper
• Detecting features in spatial point processes with clutter via model-based clustering

  1998cited by this paper
• Trimmed $k$-means: an attempt to robustify quantizers

  1997cited by this paper
• Nonlinear Inference and Cluster‐Weighted Modeling

  1997cited by this paper
• Weak Convergence and Empirical Processes: With Applications to Statistics

  1996cited by this paper
• Mixtures of linear regressions

  1989cited by this paper
• A Constrained Formulation of Maximum-Likelihood Estimation for Normal Mixture Distributions

  1985influential reference
• Some Effects of Inharmonic Partials on Interval Perception

  1984cited by this paper
• Efficient Bounded-Influence Regression Estimation

  1982cited by this paper
• Estimating the components of a mixture of normal distributions

  1969cited by this paper
• Computational Statistics and Data Analysis

  year unknowncited by this paper

• Robust clustering based on trimming

  2024cites this paper
• Uncover mortality patterns and hospital effects in COVID-19 heart failure patients: a novel Multilevel logistic cluster-weighted modeling approach

  2024cites this paper
• The finite mixture model for the tails of distribution: Monte Carlo experiment and empirical applications

  2024cites this paper
• Parsimonious Seemingly Unrelated Contaminated Normal Cluster-Weighted Models

  2024cites this paper
• Flexible mixture regression with the generalized hyperbolic distribution

  2023cites this paper
• T O GET THE BEST , TAME THE BEAST : ROBUST ML ESTIMATION FOR MIXTURE MODELS

  2023cites this paper
• Graphical and Computational Tools to Guide Parameter Choice for the Cluster Weighted Robust Model

  2022cites this paper
• Robust mixture regression via an asymmetric exponential power distribution

  2022cites this paper
• Spatially and Robustly Hybrid Mixture Regression Model for Inference of Spatial Dependence

  2021cites this paper
• Semiautomatic robust regression clustering of international trade data

  2021cites this paper
• Parameter Choice, Stability and Validity for Robust Cluster Weighted Modeling

  2021cites this paper
• Covariance matrices of S robust regression estimators

  2021cites this paper
• A note on the consistency of the maximum likelihood estimator under multivariate linear cluster-weighted models

  2020cites this paper
• Covariance matrix estimation of the maximum likelihood estimator in multivariate clusterwise linear regression

  2020cites this paper
• Weighted likelihood latent class linear regression

  2020cites this paper
• A New Algorithm using Component-wise Adaptive Trimming For Robust Mixture Regression

  2020cites this paper
• Covariance matrix estimation of the maximum likelihood estimator in multivariate clusterwise linear regression

  2020cites this paper
• A Selective Overview and Comparison of Robust Mixture Regression Estimators

  2019cites this paper
• Anomaly and Novelty detection for robust semi-supervised learning

  2019cites this paper
• Assessing trimming methodologies for clustering linear regression data

  2018cites this paper
• Book of Short Papers

  2018cites this paper
• Inverse regression approach to robust nonlinear high-to-low dimensional mapping

  2018cites this paper
• Outlier-free merging of homogeneous groups of pre-classified observations under contamination

  2017cites this paper
• Robust mixture regression modeling based on the generalized M (GM)-estimation method

  2015cites this paper