Menu
Log in


NSW Branch: A notion of depth for curve data by Dr Pierre Lafaye de Micheaux

  • 24 Sep 2019
  • 6:00 PM - 7:30 PM
  • 17 Wally's Walk, Macquarie Park NSW 2109

Venue: 17WW Collaborative Forum (Previously known as C5C), Macquarie University
17 Wally's Walk, Macquarie Park NSW 2109

A notion of depth for curve data

Following the seminal idea of John W. Tukey, statistical data depth is a function that determines centrality of an arbitrary point w.r.t. a data cloud or a probability measure. During the last decades, data depth rapidly developed to a powerful machinery proving to be useful in various fields of science. Recently, implementing the idea of depth in the functional setting attracted a lot of attention among theoreticians and applicants. We suggest a halfspace-based notion of data depth suitable for data represented as curves, or trajectories, which inherits both Euclidean-geometry and functional properties but overcomes certain limitations of the previous approaches. It can be shown that the Tukey curve depth satisfies the requirements posed on the general depth function, which are meaningful for trajectories. Application of the Tukey curve depth is illustrated on brain imaging.

Biography

Pierre Lafaye de Micheaux (Lafaye de Micheaux is the surname) is a Canadian/French/Swiss statistician, born in France in 1973. After two post-docs at the Centre de Recherches Mathématiques de Montréal, and at the Brain Imaging Center of McGill University, he got an Assistant Professor position at Grenoble Alps University in 2003. From 2009 to 2010, he was also an Affiliate Researcher at the Grenoble Neuroscience Institute. In 2009, he moved to the Department of Mathematics and Statistics, Université de Montréal, as an Assistant Professor. He was promoted to the Associate Professor level in 2011. From 2013 to 2014 he was a Senior Visiting Fellow to the Centre for Healthy Brain Ageing (School of Psychiatry) of UNSW Sydney. In 2015, he moved for almost two years to the French Engineering school of Statistics and Analysis of Information (CREST-ENSAI), as a Professor of Statistics. He joined the School of Mathematics and Statistics of UNSW Sydney in 2017.

Pierre Lafaye de Micheaux works on both Mathematical and Applied Statistics, as well as on the development of R packages and on industrial applications (such as Machine Learning or Deep Learning techniques). His main research interests are listed below. He (co)-leads three research groups: Dependence Measures, (Neuro)Imaging Genetics and Data Science and IoT.
Powered by Wild Apricot Membership Software