Professor David Warton, Ecostats Research Group, University of New South Wales, Australia, will present the Department of Statistical Science seminar with a talk entitled, "Hierarchical modelling of high-dimensional abundances in community ecology".

David Warton is a Professor and Australian Research Council Future Fellow in the Department of Statistics at the University of New South Wales. David is best known for his work on model-based multivariate analyses including the development of the mvabund R package. Most of his publications are in the areas of multivariate analyses, species distribution modelling and allometry, David champions the movement away from traditional methods of exploratory multivariate analyses to more predictive and testable model-based analyses in an effort to maintain the integrity of the data during analyses.

Abstract: Multivariate abundances in ecology are challenging to model, being high-dimensional, discrete responses with many zeros.  Technological advances have recently enabled a new class of multivariate models for such data, with the potential to specify a statistical model for abundances jointly across many taxa, to simultaneously explore interactions across taxa and the response of abundance to environmental variables.  Hierarchical models, using a factor analytical approach to capture correlation, can be used for several purposes of interest to ecologists, including estimating patterns of residual correlation across taxa, ordination, multivariate inference about environmental effects and environment-by-trait interactions, accounting for missing predictors, and improving predictions in situations where one can leverage knowledge of some species to predict others. We demonstrate this by example, discuss recently developed computation tools, and future directions