R. Pintelon et al., ANALYSES, DEVELOPMENT, AND APPLICATIONS OF TLS ALGORITHMS IN FREQUENCY-DOMAIN SYSTEM-IDENTIFICATION, SIAM journal on matrix analysis and applications (Print), 19(4), 1998, pp. 983-1004
This paper gives an overview of frequency domain total least squares (
TLS) estimators for rational transfer function models of linear time-i
nvariant multivariable systems. The statistical performance of the dif
ferent approaches are analyzed through their equivalent cost functions
. Both generalized and bootstrapped total least squares (GTLS and BTLS
) methods require the exact knowledge of the noise covariance matrix.
The paper also studies the asymptotic (the number of data points going
to infinity) behavior of the GTLS and BTLS estimators when the exact
noise covariance matrix is replaced by the sample noise covariance mat
rix obtained from a (small) number of independent data sets. Even if o
nly two independent repeated observations are available, it is shown t
hat the estimates are still strongly consistent without any increase i
n the asymptotic uncertainty.