CMStatistics 2017: Start Registration
View Submission - CMStatistics
B0300
Title: Advances in robust estimation of skew normal mixtures Authors:  Luis Angel Garcia-Escudero - Universidad de Valladolid (Spain)
Agustin Mayo-Iscar - Universidad de Valladolid (Spain)
Geoffrey McLachlan - University of Queensland (Australia)
Francesca Greselin - University of Milano Bicocca (Italy) [presenting]
Abstract: To extend the applicability of classic mixtures to dataset presenting asymmetry, mixtures of skew normal distributions are considered. A robust approach for their estimation allow us to analyze also data affected by outliers or deviations from model assumptions. Some issues related to truncated moment estimation are presented, and methods to overcome their awkward estimation will be discussed, also through applications to real data.