ACCURACY OF SOME ROBUST ESTIMATORS BASED UPON PREFILTERING OF THE INPUT OUTPUT DATA

By prefiltering the input/output data and employing certain decentralized estimation techniques, it is possible to improve the robustness of some estimators significantly. Earlier papers on these techniques have been focused on local convergence properties of four bootstrap estimators, a LS variant and three IV variants, global convergence properties of the LS variant, and convergence rates of the LS variant and two of the IV variants when the underlying system is stiff. This paper is devoted to the accuracy properties of the LS variant and one of the IV variants.