One of my two main research areas is model-based clustering, with a particular focus on clustering categorical data using finite mixture models. I work with Ivy Liu, Richard Arnold, Shirley Pledger and Daniel Fernández. I am the maintainer of the clustord R package for clustering ordinal data (https://github.com/vuw-clustering/clustord) and I am an Associate Editor for the Journal of Classification. 

My other main research area is population genetics, covering visualization, measures of genetic diversity, and clustering populations using genetic data and additional covariates such as isotope proportions. I am the author of the geneplot R package (https://github.com/lfmcmillan/geneplot) that visualizes genetic assignment and the level of genetic separation between populations.

I welcome enquiries from prospective PhD students interested in model-based clustering or statistics for population genetics. If you are interested, please my journal articles Fernandez, Epifanio and McMillan (2021) or McMillan and Fewster (2017) to decide whether your interests are well-aligned with mine. When enquiring, please send me your CV and academic transcripts. 

I teach data science and statistics courses, including topics on mathematical skills, R programming, communication and ethics.

During my undergraduate studies in mathematics I focused on particle physics and general relativity, but also studied complex analysis and differential geometry. After completing an MMath (colloquially known as "Part III") I worked for 4 years as a technical consultant, analysing data and developing algorithms for a wide range of industries including space, transport, defence and medical technology. I then worked for an operations research company, before moving to Auckland to do a masters degree in statistics. I also worked on several projects with Te Kupenga Hauora Māori within the Faculty of Medical and Health Sciences at the University of Auckland, analysing data relating to student outcomes.