Editorial: Journal of Classification Vol. 38-3

The Journal of Classification's latest issue presents ten groundbreaking articles, each contributing unique advancements in classification and clustering techniques. Chen et al. introduce two innovative algorithms for clustering brain activity data, while Michis develops a wavelet multidimensional scaling approach for economic sentiment analysis. Ballante et al. propose polarized classification trees and compare their performance with established methods. Köhn and Chiu delve into the completeness conditions of unstructured Q-matrices for the DINA model. De Raadt et al. compare reliability coefficients for ordinal rating scales. Ke and Chang present a subject selection method for non-parametric model-based classifiers. Tomarchio et al. extend cluster-weighted models to the matrix variate case. Lu et al. introduce a reversible-jump Markov chain Monte Carlo procedure for parameter estimation in parsimonious Gaussian mixture models. Soffritti develops three approaches for estimating the covariance matrix of the maximum likelihood estimator under a linear CWM. Finally, Casa et al. propose a co-clustering approach for time-dependent data, illustrated through an application to COVID-19 pandemic data across 38 countries.