In the first article, Aschenbruck, Szepannek and Wilhelm introduce two approaches for clustering mixed-type data with missingness. In the second contribution, Oh and Seo offer a new and interesting take on cluster-weighted models. The third paper, by Salehi, Bekker and Arashi, concerns semi-parametric kernel density estimation and its application for clustering. In the fourth paper, Simone uses three case studies to illustrate a new method for performing diagnostics for binomial regression trees for ordinal data.

In the fifth paper, Lux and Rinderle-Ma consider the problem of clustering one-dimensional data so that they are evenly distributed over a fixed number of low-variance clusters. In the sixth paper of this issue, Dang, Gallaugher, Browne and McNicholas introduce a skewed analogue of the power exponential distribution and use mixtures thereof for clustering. The penultimate paper, by Diao and Yi, considers the impact of mismeasured responses on classification trees. The impact using standard approaches is studied together with the impact when a novel algorithm is used. In the final article of this issue, Geisler, Ray and Xie tackle the notoriously difficult problem of identifying the minority class under extreme class imbalance. Their approach, which uses a novel approach within the loss function, is shown to perform well in examples.