Influence function and maximum bias of projection depth based estimators. (English) Zbl 1105.62350

Zuo, Yijun; Cui, Hengjian; Young, Dennis

Ann. Stat. 32, No. 1, 189-218 (2004).

Summary: Location estimators induced from depth functions increasingly have been pursued and studied in the literature. Among them are those induced from projection depth functions. These projection depth based estimators have favorable properties among their competitors. In particular, they possess the best possible finite sample breakdown point robustness. However, robustness of estimators cannot be revealed by the finite sample breakdown point alone. The influence function, gross error sensitivity, maximum bias and contamination sensitivity are also important aspects of robustness. In this article, we study these other robustness aspects of two types of projection depth based estimators: projection medians and projection depth weighted means. The latter includes the Stahel-Donoho estimator as a special case. Exact maximum bias, the influence function, and contamination and gross error sensitivity are derived and studied for both types of estimators. Sharp upper bounds for the maximum bias and the influence functions are established. Comparisons based on these robustness criteria reveal that the projection depth based estimators enjoy desirable local as well as global robustness and are very competitive among their competitors.

MSC:

62H12	Estimation in multivariate analysis
62F35	Robustness and adaptive procedures (parametric inference)
62F12	Asymptotic properties of parametric estimators
62H05	Characterization and structure theory for multivariate probability distributions; copulas

Keywords:

maxiumum bias; influence function; contamination sensitivity; gross error sensitivity; projection depth; projection median; weighted mean; robustness; breakdown point

References:

[1]	Adrover, J. and Yohai, V. J. (2002). Projection estimates of multivariate location. Ann. Statist. 30 1760–1781. · Zbl 1015.62057 · doi:10.1214/aos/1043351256
[2]	Chen, Z. and Tyler, D. E. (2002). The influence function and maximum bias of Tukey’s median. Ann. Statist. 30 1737–1759. · Zbl 1015.62058 · doi:10.1214/aos/1043351255
[3]	Cui, H. and Tian, Y. (1994). Estimation of the projection absolute median deviation and its application. J. Systems Sci. Math. Sci. 14 63–72 (in Chinese). · Zbl 0826.62048
[4]	Donoho, D. L. and Gasko, M. (1992). Breakdown properties of location estimates based on halfspace depth and projected outlyingness. Ann. Statist. 20 1803–1827. JSTOR: · Zbl 0776.62031 · doi:10.1214/aos/1176348890
[5]	Eaton, M. L. (1981). On the projections of isotropic distributions. Ann. Statist. 9 391–400. JSTOR: · Zbl 0463.62016 · doi:10.1214/aos/1176345404
[6]	Fang, K. T., Kotz, S. and Ng, K. W. (1990). Symmetric Multivariate and Related Distributions . Chapman and Hall, London. · Zbl 0699.62048
[7]	Hampel, F. R., Ronchetti, E. M., Rousseeuw, P. J. and Stahel, W. A. (1986). Robust Statistics: The Approach Based on Influence Functions . Wiley, New York. · Zbl 0593.62027
[8]	He, X. and Simpson, D. G. (1993). Lower bounds for contamination bias: Globally minimax versus locally linear estimation. Ann. Statist. 21 314–337. JSTOR: · Zbl 0770.62023 · doi:10.1214/aos/1176349028
[9]	Huber, P. J. (1964). Robust estimation of a location parameter. Ann. Math. Statist. 35 73–101. · Zbl 0136.39805 · doi:10.1214/aoms/1177703732
[10]	Liu, R. Y. (1990). On a notion of data depth based on random simplices. Ann. Statist. 18 405–414. JSTOR: · Zbl 0701.62063 · doi:10.1214/aos/1176347507
[11]	Liu, R. Y. (1992). Data depth and multivariate rank tests. In \(L_1\)-Statistical Analysis and Related Methods (Y. Dodge, ed.) 279–294. North-Holland, Amsterdam.
[12]	Liu, R. Y., Parelius, J. M. and Singh, K. (1999). Multivariate analysis by data depth: Descriptive statistics, graphics and inference (with discussion). Ann. Statist. 27 783–858. · Zbl 0984.62037 · doi:10.1214/aos/1018031260
[13]	Maronna, R. A. and Yohai, V. J. (1995). The behavior of the Stahel–Donoho robust multivariate estimator. J. Amer. Statist. Assoc. 90 330–341. JSTOR: · Zbl 0820.62050 · doi:10.2307/2291158
[14]	Martin, D. R., Yohai, V. J. and Zamar, R. H. (1989). Min–max bias robust regression. Ann. Statist. 17 1608–1630. JSTOR: · Zbl 0713.62068 · doi:10.1214/aos/1176347384
[15]	Romanazzi, M. (2001). Influence function of halfspace depth. J. Multivariate Anal. 77 138–161. · Zbl 1033.62047 · doi:10.1006/jmva.2000.1929
[16]	Rousseeuw, P. J. and Ruts, I. (1998). Constructing the bivariate Tukey median. Statist. Sinica 8 828–839. · Zbl 0905.62029
[17]	Tukey, J. W. (1975). Mathematics and the picturing of data. In Proceedings of the International Congress of Mathematicians 2 523–531. Canadian Math. Congress, Montreal. · Zbl 0347.62002
[18]	Tyler, D. E. (1994). Finite sample breakdown points of projection based multivariate location and scatter statistics. Ann. Statist. 22 1024–1044. JSTOR: · Zbl 0815.62015 · doi:10.1214/aos/1176325510
[19]	Zuo, Y. (2003). Projection-based depth functions and associated medians. Ann. Statist. 31 1460–1490. · Zbl 1046.62056 · doi:10.1214/aos/1065705115
[20]	Zuo, Y., Cui, H. and He, X. (2004). On the Stahel–Donoho estimator and depth-weighted means for multivariate data. Ann. Statist. 32 169–190. · Zbl 1105.62349 · doi:10.1214/aos/1079120132
[21]	Zuo, Y. and Serfling, R. (2000a). On the performance of some robust nonparametric location measures relative to a general notion of multivariate symmetry. J. Statist. Plann. Inference 84 55–79. · Zbl 1131.62305 · doi:10.1016/S0378-3758(99)00142-1
[22]	Zuo, Y. and Serfling, R. (2000b). General notions of statistical depth function. Ann. Statist. 28 461–482. · Zbl 1106.62334 · doi:10.1214/aos/1016218226