The Canadian Journal of Statistics Award is awarded annually by the SSC to the author(s) of an article published in the previous year in the journal, in recognition of the outstanding quality of the paper's methodological innovation and presentation.
Meixi Chen completed her PhD and MMath in Statistics at the University of Waterloo, and her BSc in Mathematics and Statistics at the University of Toronto. Her doctoral research focused on approximate Bayesian computation with applications in meteorological and biological data.
Reza Ramezan is an Associate Professor, Teaching Stream, with an active research program in the Department of Statistics and Actuarial Science at the University of Waterloo. Prior to joining Waterloo, he was an Assistant Professor of Statistics at California State University, Fullerton. He earned his PhD in Statistics from the University of Waterloo in 2014. His main research interests lie at the intersection of statistics and neuroscience, focusing on multivariate point processes, computational & high-dimensional statistical methods, multiscale modelling, machine learning, and latent variable models.
Martin Lysy is Associate Professor and Director of the Statistical Consulting and Survey Research Unit in the Department of Statistics and Actuarial Science at the University of Waterloo. Martin's research interests include modeling of biophysical and spatiotemporal processes, as well as computational methods in statistics and machine learning.
"The article entitled “Fast and scalable inference for spatial extreme value models” by Meixi Chen, Reza Ramezan, and Martin Lysy is recognized for its clear presentation of an important methodological advancement in spatial extreme value analysis.
This article develops a computationally efficient Bayesian inference framework for spatial generalized extreme value models by combining Laplace approximation with a sparsity-inducing spatial covariance technique. The proposed methodology achieves substantial gains in scalability while maintaining strong inferential accuracy, as demonstrated through simulation studies and a real data application."