ROBUST ESTIMATION OF MEASUREMENT ERROR VARIANCE COVARIANCE FROM PROCESS SAMPLING DATA/

Authors
CHEN J BANDONI A ROMAGNOLI JA
Citation
J. Chen et al., ROBUST ESTIMATION OF MEASUREMENT ERROR VARIANCE COVARIANCE FROM PROCESS SAMPLING DATA/, Computers & chemical engineering, 21(6), 1997, pp. 593-600
Citations number
8
Categorie Soggetti
Computer Application, Chemistry & Engineering","Engineering, Chemical","Computer Science Interdisciplinary Applications
Journal title
Computers & chemical engineering → ACNP
ISSN journal
00981354
Volume
21
Issue
6
Year of publication
1997
Pages
593 - 600
Database
ISI
SICI code
0098-1354(1997)21:6<593:REOMEV>2.0.ZU;2-5
Abstract
Classical approaches to variance/covariance estimations are very sensi tive to outliers. In the present paper a robust approach, based on an M-estimator, is proposed. Monte Carlo simulations show that the strate gy provides better results than conventional indirect methods under th e presence of outliers. Two examples of application are provided; deal ing with both uncorrelated and correlated errors. (C) 1997 Elsevier Sc ience Ltd.