Quantile-based clustering

DOI10.1214/19-EJS1640MaRDI QIDQ107146zbMATH OpenFDO

Authors Christian Hennig, Cinzia Viroli, Laura Anderlucci, Christian Hennig, Cinzia Viroli

Publication date 1 January 2019

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1806.10403, https://projecteuclid.org/euclid.ejs/1575428462

zbMATH Keywords

fixed partition modelhigh dimensional clusteringnonparametric mixturequantile discrepancy

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Abstract: A new cluster analysis method, $K$-quantiles clustering, is introduced. $K$-quantiles clustering can be computed by a simple greedy algorithm in the style of the classical Lloyd's algorithm for $K$-means. It can be applied to large and high-dimensional datasets. It allows for within-cluster skewness and internal variable scaling based on within-cluster variation. Different versions allow for different levels of parsimony and computational efficiency. Although $K$-quantiles clustering is conceived as nonparametric, it can be connected to a fixed partition model of generalized asymmetric Laplace-distributions. The consistency of $K$-quantiles clustering is proved, and it is shown that $K$-quantiles clusters correspond to well separated mixture components in a nonparametric mixture. In a simulation, $K$-quantiles clustering is compared with a number of popular clustering methods with good results. A high-dimensional microarray dataset is clustered by $K$-quantiles.

Recommendations

• A Method for Cluster Analysis Based on Projections and Quantile-Quantile Plots
• Pseudo-quantile functional data clustering
• \(K\)-expectiles clustering
• Regularized \(k\)-means clustering of high-dimensional data and its asymptotic consistency
• Quantile-based classifiers

Cites work

• scientific article; zbMATH DE number 5430929 (Why is no real title available?)
• scientific article; zbMATH DE number 3942813 (Why is no real title available?)
• scientific article; zbMATH DE number 4076317 (Why is no real title available?)
• scientific article; zbMATH DE number 44579 (Why is no real title available?)
• A multivariate and asymmetric generalization of Laplace distribution
• A statistical view of clustering performance through the theory of U-processes
• Asymptotic Statistics
• Asymptotic behaviour of classification maximum likelihood estimates
• Clustering Objects on Subsets of Attributes (with Discussion)
• Clustering by passing messages between data points
• Clustering strategy and method selection
• Consistency of spectral clustering
• Finding Groups in Data
• Finite mixture models
• Generating random correlation matrices based on partial correlations
• Least squares quantization in PCM
• Method-independent indices for cluster validation and estimating the number of clusters
• Mixtures of distance-based models for ranking data
• NON-NULL RANKING MODELS. I
• Nearest neighbor clustering: a baseline method for consistent clustering with arbitrary objective functions
• Probabilistic d-clustering
• Quantile-based classifiers
• Quantile-based clustering
• Rates of convergence in the source coding theorem, in empirical quantizer design, and in universal lossy source coding
• Resampling methods for exploring cluster stability
• Strong consistency of k-means clustering
• The effectiveness of Lloyd-type methods for the \(k\)-means problem
• Weighting and selection of variables for cluster analysis

Cited in

(6)

• A Method for Cluster Analysis Based on Projections and Quantile-Quantile Plots
• \(K\)-expectiles clustering
• Quantization-based clustering algorithm
• Hierarchical conceptual clustering based on quantile method for identifying microscopic details in distributional data
• QuClu
• Quantile-based clustering

Describes a project that uses

Uses Software

• clusfind
• COSA
• APCluster
• apcluster

This page was built for publication: Quantile-based clustering

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q107146)