An efficient $k$-means-type algorithm for clustering datasets with incomplete records

Abstract

The $k$-means algorithm is arguably the most popular nonparametric clustering method but cannot generally be applied to datasets with incomplete records. The usual practice then is to either impute missing values under an assumed missing-completely-at-random mechanism or to ignore the incomplete records, and apply the algorithm on the resulting dataset. We develop an efficient version of the $k$-means algorithm that allows for clustering in the presence of incomplete records. Our extension is called $k_m$-means and reduces to the $k$-means algorithm when all records are complete. We also provide initialization strategies for our algorithm and methods to estimate the number of groups in the dataset. Illustrations and simulations demonstrate the efficacy of our approach in a variety of settings and patterns of missing data. Our methods are also applied to the analysis of activation images obtained from a functional Magnetic Resonance Imaging experiment.

arXiv comment21 pages, 12 figures, 3 tables, in press, Statistical Analysis and Data Mining -- The ASA Data Science Journal, 2018

References in corpus (9)

• The Fourth BATSE Gamma-Ray Burst Catalog (Revised)
• The ultra-long Gamma-Ray Burst 111209A: the collapse of a blue supergiant?
• $k$-POD: A Method for $k$-Means Clustering of Missing Data
• Short vs. Long Gamma-Ray Bursts: A Comprehensive Study of Energetics and Prompt Gamma-Ray Correlations
• A Re-defined and Generalized Percent-Overlap-of-Activation Measure for Studies of fMRI Reproducibility and its Use in Identifying Outlier Activation Maps
• Gaussian-Mixture-Model-based Cluster Analysis Finds Five Kinds of Gamma Ray Bursts in the BATSE Catalog
• Assessing Certainty of Activation or Inactivation in Test-Retest fMRI Studies
• The puzzling interpretation of NIR indices: The case of NaI2.21
• Multivariate $t$-Mixtures-Model-based Cluster Analysis of BATSE Catalog Establishes Importance of All Observed Parameters, Confirms Five Distinct Ellipsoidal Sub-populations of Gamma Ray Bursts

Cited by in corpus (2)

• Kernel-estimated Nonparametric Overlap-Based Syncytial Clustering
• Fast model-based clustering of partial records