Analogues on the Sphere of the Affine-Equivariant Spatial Median

Janice L. Scealy and Andrew T. A. Wood

Journal of the American Statistical Association, 2021, vol. 116, issue 535, 1457-1471

Abstract: Robust estimation of location for data on the unit sphere Sp−1 is an important problem in directional statistics even though the influence functions of the sample mean direction and other location estimators are bounded. A significant limitation of previous literature on this topic is that robust estimators and procedures have been developed under the assumption that the underlying population is rotationally symmetric. This assumption often does not hold with real data and in these cases there is a needless loss of efficiency in the estimator. In this article, we propose two estimators for spherical data, both of which are analogous to the affine-equivariant spatial median in Euclidean space. The influence functions of the new location estimators are obtained under a new semiparametric elliptical symmetry model on the sphere and are shown to be standardized bias robust in the highly concentrated case; the influence function of the companion scatter matrix is also obtained. An iterative algorithm that computes both estimators is described. Asymptotic results, including consistency and asymptotic normality, are also derived for the location estimators that result from applying a fixed number of steps in this algorithm. Numerical studies demonstrate that both location estimators may be expected to perform well in practice in terms of efficiency and robustness. A brief example application from the geophysics literature is also provided. Supplementary materials for this article are available online.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://hdl.handle.net/10.1080/01621459.2020.1733582 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:jnlasa:v:116:y:2021:i:535:p:1457-1471

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/UASA20

DOI: 10.1080/01621459.2020.1733582

Access Statistics for this article

Journal of the American Statistical Association is currently edited by Xuming He, Jun Liu, Joseph Ibrahim and Alyson Wilson

More articles in Journal of the American Statistical Association from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().