Editorial: Journal of Classification Vol. 38-2

The editorial for the Journal of Classification's second issue of 2021 begins with a note of gratitude to the Associate Editors for their dedication. The issue features ten articles, each contributing significantly to the field of clustering. Notably, Ng and Murphy introduce a model-based clustering approach using Gaussian Cox processes, while Ellenbach et al. explore methods for tuning parameter values in prediction rules. Torrente and Romo present a novel initialization method for k-means clustering, and Chacón discusses explicit agreement extremes for clustering comparisons. McNicholas et al. develop an evolutionary algorithm for parameter estimation, and Thrun and Ultsch employ projection-based clustering for high-dimensional data. Młodak considers contiguity constraints in clustering, Fioravanti and Tohmé delve into axioms for group identification, and Randriamihamison et al. examine contiguity constraints for Ward’s hierarchical agglomerative clustering. Ogasawara concludes the issue with a discussion on agreement coefficients for multiple raters. Each article offers unique insights and methodologies that advance the understanding and application of clustering techniques.