Title :
Constrained logarithmic least squares in parameter estimation
Author :
Bai, Er-Wei ; Ye, Yinyu
Author_Institution :
Dept. of Electr. & Comput. Eng., Iowa Univ., Iowa City, IA, USA
Abstract :
This paper first shows that while robust in terms of the average output error, the least squares estimate is sensitive to outliers with respect to the maximum output error. In fact the worst case output error of the least squares can go unbounded. Then, a constrained logarithmic least squares for system identification is proposed. Analytic center algorithms are presented to solve this constrained logarithmic least squares problem.
Keywords :
discrete time systems; least squares approximations; minimax techniques; parameter estimation; SISO systems; constrained logarithmic least squares; discrete time systems; identification; minimax technique; output error; parameter estimation; Algorithm design and analysis; Cities and towns; Least squares approximation; Least squares methods; Minimax techniques; Noise measurement; Parameter estimation; Robustness; System identification; Transfer functions;
Journal_Title :
Automatic Control, IEEE Transactions on
