Title :
Bounds for identification error and a quantitative measure of identifiability
Author_Institution :
Systems Control Inc., Palo Alto, California
Abstract :
In this paper, upper and lower bounds for identification error are established for finite observation samples. It was shown that the behavior of both the upper and lower bounds are described completely by a resolvability function which describes the degree of resolvability between different parameters in the parameter set. This allows one to derive identifiability conditions by investigating the asymptotic behavior of this function. Moreover, the resolvability function gives a quantitative measure of identifiability.
Keywords :
Bismuth; Control systems; Density functional theory; Eigenvalues and eigenfunctions; Error correction; Extraterrestrial measurements; Milling machines; Statistical distributions; System identification; Systems engineering and theory;
Conference_Titel :
Decision and Control including the 13th Symposium on Adaptive Processes, 1974 IEEE Conference on
Conference_Location :
Phoenix, AZ, USA
DOI :
10.1109/CDC.1974.270475
