Robust Improper Maximum Likelihood: Tuning, Computation, and a Comparison With Other Methods for Robust Gaussian Clustering

Abstract

The two main topics of this article are the introduction of the "optimally tuned robust improper maximum likelihood estimator"(OTRIMLE) for robust clustering based on the multivariate Gaussian model for clusters, and a comprehensive simulation study comparing the OTRIMLE to maximum likelihood in Gaussian mixtures with and without noise component, mixtures of t-distributions, and the TCLUST approach for trimmed clustering. The OTRIMLE uses an improper constant density for modeling outliers and noise. This can be chosen optimally so that the nonnoise part of the data looks as close to a Gaussian mixture as possible. Some deviation from Gaussianity can be traded in for lowering the estimated noise proportion. Covariance matrix constraints and computation of the OTRIMLE are also treated. In the simulation study, all methods are confronted with setups in which their model assumptions are not exactly fulfilled, and to evaluate the experiments in a standardized way by misclassification rates, a new model-based definition of "true clusters" is introduced that deviates from the usual identification of mixture components with clusters. In the study, every method turns out to be superior for one or more setups, but the OTRIMLE achieves the most satisfactory overall performance. The methods are also applied to two real datasets, one without and one with known "true" clusters. Supplementary materials for this article are available online.

Projection-Based Clustering through Self-Organization and Swarm Intelligence

“…Each module of DBS was compared with various competing algorithms, and in the majority of cases, the modules outperformed those algorithms. However, the author of this work concurs with [Coretto/Hennig, 2016] that despite one's best intentions and efforts to conduct fair comparisons of various methods of visualization, projection and clustering, "ultimately it would be good to have comparisons of methods run by researchers who did not have their hand in the design of any of the methods"; this is because "(simulation) studies can always be designed that make any method 'win.' " The author also agrees with [Coretto/Hennig, 2016] that "readers need to make up their own mind about to what extent our study covered situations that are important to them."…”

Wild adaptive trimming for robust estimation and cluster analysis

“…A refined estimate of the population sizes, as well as a refined identification of group membership, could be obtained by adding a confirmatory step to the tentative clustering that we obtain by our divisive procedure. The confirmatory step could also help separate small and concentrated groups of contaminated observations from background noise (Hennig & Liao, ; Coretto & Hennig, ) and highlight the relationship between our procedure and the robust fitting of mixture models. Both these topics are the subject of ongoing research.…”

Improving Many Volatility Forecasts Using Cross-Sectional Volatility Clusters

“…The term noise here is inherited from the robust clustering and classification literature (see Ritter 2014), where it is understood as a "noisy cluster", that is, a cluster of points with an unstructured shape compared with the main groups in the population. The uniform distribution is a convenient choice to capture atypical group of points not having a central location, and that are scattered in density regions somewhat separated from the main bulk of the data (Banfield and Raftery 1993;Coretto and Hennig 2016;Hennig 2004).…”