Simulated annealing for higher dimensional projection depth

Wei Shao and Yijun Zuo

Computational Statistics & Data Analysis, 2012, vol. 56, issue 12, 4026-4036

Abstract: Data depth for multivariate data has received considerable attention in multivariate nonparametric analysis and robust statistics. Nevertheless, the computation of data depth such as projection depth has remained as a very challenging problem which hinders the development of the projection depth and its wide use in practice. Especially in high dimension, there is no efficient algorithm for the computation of the projection depth and its induced estimators (including the Stahel–Donoho estimator as a special case). In this paper, we employ simulated annealing algorithm by invoking Markov Chain Monte Carlo technique to compute the projection depth. Simulation results show that this new approximate method performs significantly better than its competitors. In lower dimension, we are able to show that the approximate results from this algorithm are very close to the exact ones.

Keywords: Projection depth; Approximate algorithm; Simulated annealing; Markov Chain Monte Carlo (search for similar items in EconPapers)
Date: 2012
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0167947312001843
Full text for ScienceDirect subscribers only.

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:eee:csdana:v:56:y:2012:i:12:p:4026-4036

DOI: 10.1016/j.csda.2012.05.002

Access Statistics for this article

Computational Statistics & Data Analysis is currently edited by S.P. Azen

More articles in Computational Statistics & Data Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().