MULTIVARIATE REGRESSION S-ESTIMATORS FOR ROBUST ESTIMATION AND INFERENCE

By S. Van Aelst, Gert Willems. 2005

65 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/aac529ad46b6fcb88218e1a3458fefcaaf317a6b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Mia Hubert
2. Peter J. Rousseeuw
3. S. Van Aelst
4. Christophe Croux
5. M. Salibián‐Barrera
6. José Julio Espina Agulló
7. Gert Willems
8. Peter Filzmoser

Citations in the corpus

• The multivariate least-trimmed squares estimator (2008, methodology): “The S-estimator performs best while MLTS, RMLTS and LRMCD show similar behavior.”
• High-Breakdown Robust Multivariate Methods (2008, methodology): “Alternatively, Van Aelst and Willems (2005) introduced multivariate regression S-estimators and extended the fast robust bootstrap methodology of Salibian-Barrera and Zamar (2002) to this setting while García Ben, Martínez and Yohai (2006) proposed τ -estimators for multivariate regression.”
• Principal Components Analysis Based on Multivariate MM Estimators With Fast and Robust Bootstrap (2006, background): “APPENDIX: PROOFS Proof of Theorem 1 As given by Van Aelst and Willems (2005), for the S estimators, we have that *(#?, Tn; Xn) =min(rwr], \n-nr\ -k(Xn))/n. (A.l) Suppose that Xn is a dataset obtained from Xn by replacing m obser vations, where m < min([nr], \n ? nf] ? k(Xn)).”