Abstract
We develop a new approach to resistant estimation of multivariate location using minimum spanning trees (MSTs). The procedure prunes the MST by iteratively identifying the longest arc and removing points at its distal end. When about half the points have been pruned, the remaining data points are used to estimate location. Simulation results indicate that the pruning method performs well with data that are highly contaminated (40%) with shift outliers, whereas the minimum volume ellipsoid (MVE) performs poorly under these conditions.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callSimilar Papers
More From: Journal of Statistical Computation and Simulation
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
