Nonparametrics and Robustness in Modern Statistical Inference and Time Series Analysis: Festschrift for Jana Jureckova

0365546 - ÚTIA 2012 RIV US eng M - Část monografie knihy
Víšek, Jan Ámos
Robust error-term-scale estimate.
Nonparametrics and Robustness in Modern Statistical Inference and Time Series Analysis: Festschrift for Jana Jureckova. USA: Institute of Mathematical Statistics (IMS), 2010 - (Antoch, J.; Huskova, M.; Sen, P.), s. 254-267. Books IMS, IMS Collections, IMS Collections vol 7(2010). ISBN 978-0-940600-80-5
Grant ostatní: GA UK(CZ) GA402/09/0557
Výzkumný záměr: CEZ:AV0Z10750506
Klíčová slova: Robustness * Regression * Disturbances * Scale estimate
Kód oboru RIV: BB - Aplikovaná statistika, operační výzkum
http://library.utia.cas.cz/separaty/2011/SI/visek-robust error-term-scale estimate.pdf

A scale-equivariant and regression-invariant estimator of the variance of error terms in the linear regression model is proposed and its consistency proved. The estimator is based on (down)weighting the order statistics of the squared residuals which corresponds to the consistent and scale- and regression-equivariant estimator of the regression coefficients. A~small numerical study demonstrating the behaviour of the estimator under the various types of contamination is included.
Trvalý link: http://hdl.handle.net/11104/0200767