Asymptotics of the two-stage spatial sign correlation
From MaRDI portal
Publication:901278
DOI10.1016/J.JMVA.2015.10.011zbMATH Open1328.62335arXiv1506.02578OpenAlexW2112327425MaRDI QIDQ901278FDOQ901278
Authors: Alexander Dürre, Daniel Vogel 
Publication date: 23 December 2015
Published in: Journal of Multivariate Analysis (Search for Journal in Brave)
Abstract: The spatial sign correlation (D"urre, Vogel and Fried, 2015) is a highly robust and easy-to-compute, bivariate correlation estimator based on the spatial sign covariance matrix. Since the estimator is inefficient when the marginal scales strongly differ, a two-stage version was proposed. In the first step, the observations are marginally standardized by means of a robust scale estimator, and in the second step, the spatial sign correlation of the thus transformed data set is computed. D"urre et al. (2015) give some evidence that the asymptotic distribution of the two-stage estimator equals that of the spatial sign correlation at equal marginal scales by comparing their influence functions and presenting simulation results, but give no formal proof. In the present paper, we close this gap and establish the asymptotic normality of the two-stage spatial sign correlation and compute its asymptotic variance for elliptical population distributions. We further derive a variance-stabilizing transformation, similar to Fisher's z-transform, and numerically compare the small-sample coverage probabilities of several confidence intervals.
Full work available at URL: https://arxiv.org/abs/1506.02578
Recommendations
- Spatial sign correlation
- scientific article; zbMATH DE number 1301948
- On robust estimation of a correlation coefficient
- The asymptotic inadmissibility of the spatial sign covariance matrix for elliptically symmetric distributions
- Variance stabilizing transformation and studentization for estimator of correlation coefficient
Nonparametric estimation (62G05) Nonparametric robustness (62G35) Estimation in multivariate analysis (62H12)
Cites Work
- Title not available (Why is that?)
- A Note on Quantiles in Large Samples
- On Bahadur's Representation of Sample Quantiles
- A distribution-free M-estimator of multivariate scatter
- Asymptotic behaviour of S-estimates of multivariate location parameters and dispersion matrices
- Robust m-estimators of multivariate location and scatter
- Robust principal component analysis for functional data. (With comments)
- Constrained \(M\)-estimation for multivariate location and scatter
- Robust functional estimation using the median and spherical principal components
- Title not available (Why is that?)
- Alternatives to the Median Absolute Deviation
- A Class of Statistics with Asymptotically Normal Distribution
- Sign and rank covariance matrices
- Asymptotic distributions of robust shape matrices and scales
- Elliptical graphical modelling
- A canonical definition of shape
- Transformation of non positive semidefinite correlation matrices
- Bahadur representation for \(U\)-quantiles of dependent data
- A New Proof of the Bahadur Representation of Quantiles and an Application
- Generalized L-, M-, and R-statistics
- Some robust estimates of principal components
- The spatial sign covariance matrix with unknown location
- Spatial sign correlation
- Title not available (Why is that?)
- On the multivariate spatial median for clustered data
- Multivariate nonparametric methods with R. An approach based on spatial signs and ranks.
- Asymptotic Normality of Sample Quantiles for $m$-Dependent Processes
- The asymptotic efficiency of the spatial median for elliptically symmetric distributions
- The \(k\)-step spatial sign covariance matrix
- Title not available (Why is that?)
Cited In (3)
Uses Software
This page was built for publication: Asymptotics of the two-stage spatial sign correlation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q901278)
