Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
415394 | Computational Statistics & Data Analysis | 2014 | 6 Pages |
Abstract
A parametric family of MM-estimators of scale based on the Rousseeuw–Croux QnQn-estimator is proposed; estimator’s bias and efficiency are studied. A low-complexity one-step MM-estimator is obtained allowing a considerably faster computation with greater than 80% efficiency and the highest possible 50% breakdown point. Analytical and Monte Carlo modeling results confirm the effectiveness of the proposed approach.
Related Topics
Physical Sciences and Engineering
Computer Science
Computational Theory and Mathematics
Authors
Pavel O. Smirnov, Georgy L. Shevlyakov,