Rate of convergence of depth contours: with application to a multivariate metrically trimmed mean
In a recent paper of He and Wang (1997, Ann. Statist. 25, 495-504), they considered depth contours based on data depth and they proved a uniform contour convergence theorem under some conditions on the depth measure. In this paper we prove n-1/2 rate of convergence of depth contours using empirical process and U-process theory. This result is then applied to get n-1/2 rate of convergence of a multivariate metrically trimmed mean.
Year of publication: |
2000
|
---|---|
Authors: | Kim, Jeankyung |
Published in: |
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 49.2000, 4, p. 393-400
|
Publisher: |
Elsevier |
Keywords: | Rates of convergence Depth contours Deepest point Metrically trimmed mean Empirical process U-process |
Saved in:
Saved in favorites
Similar items by person
-
Asymptotic properties of location estimators based on projection depth
Kim, Jeankyung, (2001)
-
Asymptotic results in segmented multiple regression
Kim, Jeankyung, (2008)
-
Quantile regression with an epsilon-insensitive loss in a reproducing kernel Hilbert space
Park, Jinho, (2011)
- More ...