ANZJS Special Issue: Geoff McLachlan Festschrift

Geoff McLachlan has been an active and enduring presence within the Australian statistical community for five decades, and has produced many formative and influential works in the areas of computational statistics, discriminant analysis and classification, bioinformatics, among numerous other subjects. On the occasion of his 75th birthday, we celebrate Geoff’s storied career by presenting him with this festschrift containing 10 papers on the various themes of his career’s research.

The leading paper of Tomarchio, Ingrassia & Melnykov (2022) follows naturally from Geoff’s interest in the study of mixture of normal distributions for vectorial data, and extends such an approach to the problem domain of matrix data clustering. The works of Hui & Nghiem (2022) and Scrucca (2022) then follow, both focusing on the use of latent space representations via dimensionality reduction in order to facility better mixture-based clustering outcomes.

Durand et al. (2022), Greve et al. (2022), and Hennig & Coretto (2022) then each provide differing perspectives and solutions to the problem of clustering and mixture model estimation when the underlying number of clusters is unknown. Here, Durand et al. (2022) and Greve et al. (2022) provide Bayesian solutions for spatial regression data and vectorial data, respectively, whereas Hennig & Coretto (2022) consider an approach based on optimally tuned robust improper maximum likelihood estimation.

Nguyen & Forbes (2022) contribute with work on the verification of assumptions that are necessary for the application of online versions of the EM algorithm for the maximum likelihood estimation of broad classes of statistical models and their mixtures, and Stewart (2022) considers the error rate-related problem of hypothesis test detection boundary characterisation, when data may arise from finite mixture families under the alternative hypothesis.

Lastly, the Festschrift concludes with the works of Arief et al. (2022) and Zhang, Swallow & Gupta (2022), who study genomic prediction of plant genotype data and subpopulations in human genome-wide association data, respectively.

The festschrift is free to read for a limited time and in addition, many articles are open access:


More Details