AN EXTENDED MARQUARDT-TYPE PROCEDURE FOR FITTING ERROR-IN-VARIABLES MODELS
- Additional Document Info
- View All
The paper presents a simple derivation of the method of fitting nonlinear algebraic models where all variables are subject to error and improves the numerical efficiency of the algorithm. Including a known procedure for equilibrating balance equations and factorizing the weighting matrix, the classical Gauss-Marquardt method of estimating parameters in nonlinear models is shown to handle also the error-in-variables model, thereby extending the efficiency and robustness of Marquardt's compromise to this slightly more involved case. 1985.
COMPUTERS & CHEMICAL ENGINEERING
author list (cited authors)
complete list of authors