A1018
Title: Handling outliers when clustering three-way data
Authors: Paul McNicholas - McMaster University (Canada) [presenting]
Katharine Clark - McMaster University (Canada)
Abstract: A paradigm for clustering three-way data is introduced based on matrix variate mixture models. Then, an algorithm for dealing with outliers is introduced. Crucially, this algorithm does not require pre-specification of the number of outliers. The performance of the proposed approach is demonstrated using simulated and real data.
