On depth and deep points: a calculus
Mizera, Ivan
Ann. Statist., Tome 30 (2002) no. 1, p. 1681-1736 / Harvested from Project Euclid
For a general definition of depth in data analysis a differential-like calculus is constructed in which the location case (the framework of Tukey's median) plays a fundamental role similar to that of linear functions in the mathematical analysis. As an application, a lower bound for maximal regression depth is proved in the general multidimensional case--as conjectured by Rousseeuw and Hubert and others. This lower bound is demonstrated to have an impact on the breakdown point of the maximum depth estimator.
Publié le : 2002-12-14
Classification:  Centerpoint,  compactification,  degree of mapping,  depth,  halfspace,  Kronecker index,  median,  multivariate location,  regression,  set-valued analysis,  vector optimization,  weak convergence,  62H05,  52A40,  54C60,  55M25,  90C29
@article{1043351254,
     author = {Mizera, Ivan},
     title = {On depth and deep points: a calculus},
     journal = {Ann. Statist.},
     volume = {30},
     number = {1},
     year = {2002},
     pages = { 1681-1736},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1043351254}
}
Mizera, Ivan. On depth and deep points: a calculus. Ann. Statist., Tome 30 (2002) no. 1, pp.  1681-1736. http://gdmltest.u-ga.fr/item/1043351254/