Maximum set estimators with bounded estimation error
Authors:
- 18 July 2005
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 53 (8) , 3172-3182
Abstract
We consider the linear regression problem of estimating a deterministic parameter vector x from observations y = Hx + w, where H is known, and w is additive noise. We seek an estimator whose estimation error does not exceed a given maximum error for as wide a range of conditions as possible. The maximum error is a design choice and is generally lower than the error provided by the well-known least-squares (LS) estimator. We develop estimators guaranteeing the required error for as large a parameter set as possible and for as large a noise level as possible. We discuss methods for finding these estimators and demonstrate that in many cases, the proposed estimators outperform the LS estimator.Keywords
This publication has 18 references indexed in Scilit:
- Minimax MSE-ratio estimation with signal covariance uncertaintiesIEEE Transactions on Signal Processing, 2005
- Robust mean-squared error estimation in the presence of model uncertaintiesIEEE Transactions on Signal Processing, 2004
- Estimation with maximum error requirements2004
- Linear Minimax Regret Estimation of Deterministic Parameters with Bounded Data UncertaintiesIEEE Transactions on Signal Processing, 2004
- A Competitive Minimax Approach to Robust Estimation of Random ParametersIEEE Transactions on Signal Processing, 2004
- Robust optimization ? methodology and applicationsMathematical Programming, 2002
- Robust rationality and decisions under severe uncertaintyJournal of the Franklin Institute, 2000
- On minimax robustness: A general approach and applicationsIEEE Transactions on Information Theory, 1984
- Ridge Regression: Biased Estimation for Nonorthogonal ProblemsTechnometrics, 1970
- Robust Estimation of a Location ParameterThe Annals of Mathematical Statistics, 1964