Abstract
Tukey’s halfspace median (HM), servicing as the multivariate counterpart of the univariate median, has been introduced and extensively studied in the literature. It is supposed and expected to preserve robustness property (the most outstanding property) of the univariate median. One of prevalent quantitative assessments of robustness is finite sample breakdown point (FSBP). Indeed, the FSBP of many multivariate medians have been identified, except for the most prevailing one—the Tukey’s halfspace median. This paper presents a precise result on FSBP for Tukey’s halfspace median. The result here depicts the complete prospect of the global robustness of HM in the finite sample practical scenario, revealing the dimension effect on the breakdown point robustness and complimenting the existing asymptotic breakdown point result.
Similar content being viewed by others
References
Adrover J, Yohai V. Projection estimates of multivariate location. Ann Statist, 2002, 30: 1760–1781
Bai Z D, He X M. Asymptotic distributions of the maximal depth estimators for regression and multivariate location. Ann Statist, 1999, 27: 1617–1637
Chen Z. Robustness of the half-space median. J Statist Plann Infer, 1995, 46: 175–181
Chen Z, Tyler D E. The influence function and maximum bias of Tukey’s median. Ann Statist, 2002, 30: 1737–1759
Davies P L, Gather U. Breakdown and groups. Ann Statist, 2005, 33: 977–1035
Donoho D L. Breakdown properties of multivariate location estimators. PhD Thesis. Qualifying Paper. Cambridge: Harvard University, 1982
Donoho D L, Gasko M. Breakdown properties of location estimates based on halfspace depth and projected outlyingness. Ann Statist, 1992, 20: 1808–1827
Donoho D L, Huber P J. The notion of breakdown point. In: Bickel P J, Doksum K A, Hodges J J L, eds. A Festschrift for Erich L Lehmann. Belmont: Wadsworth, 1983, 157–184
Dutta S, Ghosh A K, Chaudhuri P. Some intriguing properties of Tukey’s half-space depth. Bernoulli, 2011, 17: 1420–1434
Dyckerhoff R, Mozharovskyi P. Exact computation of the halfspace depth. Comput Statist Data Anal, 2016, 98: 19–30
Hallin M, Paindaveine D, Siman M. Multivariate quantiles and multiple-output regression quantiles: From L1 optimization to halfspace depth. Ann Statist, 2010, 38: 635–669
Hampel F R. A general qualitative definition of robustness. Ann Math Statist, 1971, 42: 1887–1896
Hodges J L. Efficiency in normal samples and tolerance of extreme values for some estimates of location. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, vol. 1. Berkeley: University California Press, 1967, 163–168
Huber P J. Robust estimation of a location parameter. Ann Math Statist, 1964, 35: 73–101
Huber P J. Robust Statisitcs. New York: Wiley, 1981
Liu R Y, Singh K. Ordering directional data: Concepts of data depth on circles and spheres. Ann Statist, 1992, 20: 1468–1484
Liu X H, Luo S H, Zuo Y J. Some results on the computing of Tukey’s halfspace median. ArXiv:1604.05927, 2016
Liu X H, Zuo Y J, Wang Z Z. Exactly computing bivariate projection depth median and contours. Comput Statist Data Anal, 2013, 60: 1–11
Lopuhaä H P, Rousseeuw P J. Breakdown points of affine equivariant estimators of multivariate location and covariance matrices. Ann Statist, 1991, 19: 229–248
L´opez-Pintado S, Romo J. On the concept of depth for functional data. J Amer Statist Assoc, 2009, 104: 718–734
Mizera I. On depth and deep points: A calculus. Ann Statist, 2002, 30: 1681–1736
Mosler K, Lange T, Bazovkin P. Computing zonoid trimmed regions of dimension d > 2. Comput Statist Data Anal, 2009, 53: 2500–2510
Oja H. Descriptive statistics for multivariate distributions. Statist Probab Lett, 1983, 1: 327–332
Paindaveine D, Siman M. On directional multiple-output quantile regression. J Multivariate Anal, 2011, 102: 193–392
Romanazzi M. Influence function of halfspace depth. J Multivariate Anal, 2002, 77: 138–161
Rousseeuw P J, Hubert M. Regression depth (with discussion). J Amer Statist Assoc, 1999, 94: 388–433
Rousseeuw P J, Ruts I. Constructing the bivariate Tukey median. Statist Sinica, 1998, 8: 827–839
Struyf A, Rousseeuw P J. High-dimensional computation of the deepest location. Comput Statist Data Anal, 2000, 34: 415–426
Tukey J W. Mathematics and the picturing of data. In: Proceedings of the International Congress of Mathematicians. Montreal: Canadian Mathematical Congress, 1975, 523–531
Weber A. Uber den Standort der Industrien, Tubingen. In: Alfred Weber’s Theory of Location of Industries. Chicago: University of Chicago Press, 1909
Zuo Y. Some quantitative relationships between two types of finite sample breakdown point. Stat Probab Lett, 2001, 51: 369–375
Zuo Y J, Serfling R. General notions of statistical depth function. Ann Statist, 2000, 28: 461–482
Acknowledgements
This work was supported by National Natural Science Foundation of China (Grant Nos. 11601197, 11461029, 71463020, 61263014 and 61563018), National Science Foundation of Jiangxi Province (Grant Nos. 20161BAB201024, 20142BAB211014, 20143ACB21012 and 20151BAB211016), the Key Science Fund Project of Jiangxi Provincial Education Department (Grant Nos. GJJ150439, KJLD13033 and KJLD14034), the National Science Fund for Distinguished Young Scholars in China (Grant No. 10725106), the National Natural Science Foundation of China (Grant Nos. General program 11171331 and Key program 11331011), a grant from the Key Lab of Random Complex Structure and Data Science, Chinese Academy of Sciences and Natural Science Foundation of Shenzhen University. The authors thank the two anonymous referees and the AE for their careful reading and insightful comments, which led to many improvements of this paper.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liu, X., Zuo, Y. & Wang, Q. Finite sample breakdown point of Tukey’s halfspace median. Sci. China Math. 60, 861–874 (2017). https://doi.org/10.1007/s11425-016-0285-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11425-016-0285-1