Results 261 to 270 of about 8,978,880 (312)

Identifiability in dynamic errors-in-variables models

The 22nd IEEE Conference on Decision and Control, 1983
Abstract. This paper is concerned with the identifiability of scalar linear dynamic errors‐in‐variables systems. The analysis is based on second moments only. The set of feasible systems corresponding to given second moments of the observations is described and conditions for identifiability are derived for the case of rational transfer functions.
Anderson, Brian D.O., Deistler, Manfred
openaire   +3 more sources

Identification in the Linear Errors in Variables Model

Econometrica, 1983
Consider the following multiple linear regression model with errors in variables: \(y_ j=\xi^ T\!_ j\beta +\epsilon_ j\), \(x_ j=\xi_ j+\nu_ j\), \(j=1,...,n\), where \(\xi_ j\), \(x_ j\), \(\nu_ j\), and \(\beta\) are k-vectors, \(y_ j\), \(\epsilon_ j\) are scalars. The \(\xi_ j\) are unobserved variables: instead the \(x_ j\) are observed.
Kapteyn, Arie, Wansbeek, Tom
openaire   +2 more sources

Identification of nonlinear errors-in-variables models

Automatica, 2002
The publication deals with a generalization of a classical eigenvalue-decomposition method first developed for errors-in-variables linear system identification. An identification algorithm is presented for nonlinear, but linear in parameters errors-in-variables models using nonlinear polynomial eigenvalue-eigenvector decompositions.
István Vajk, Jenö Hetthéssy
openaire   +1 more source

The Degenerate Bounded Errors-in-Variables Model

SIAM Journal on Matrix Analysis and Applications, 2001
The paper is devoted to a special case of the error-in-variable problem. It is viewed as total least squares with bounds on the uncertainty in the coefficient matrix. The chosen approach advantage is given as a motivation for further considerations. Corresponding proofs and algorithm synthesis are presented.
Shivkumar Chandrasekaran, Ming Gu 0002, Ali H. Sayed, Keith E. Schubert   +3 more
openaire   +1 more source

Hypotheses Testing for Error-in-Variables Models

Annals of the Institute of Statistical Mathematics, 2000
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Gimenez, Patricia, Bolfarine, Heleno, Colosimo, Enrico A.   +2 more
openaire   +1 more source

Bootstrapping Errors-in-Variables Models

2000
The bootstrap is a numerical technique, with solid theoretical foundations, to obtain statistical measures about the quality of an estimate by using only the available data. Performance assessment through bootstrap provides the same or better accuracy than the traditional error propagation approach, most often without requiring complex analytical ...
Bogdan Matei, Peter Meer
openaire   +1 more source

Estimation in the polynomial errors-in-variables model

Science China Mathematics, 2002
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Zhang, Sanguo, Chen, Xiru
openaire   +1 more source

On errors-in-variables for binary regression models

Biometrika, 1984
The authors consider binary regression models when the predictors have errors. Assuming that nuisance parameters are independently and normally distributed, the conditional likelihood was derived. When the measurement error is large, the usual estimates are unreliable and in this situation, the authors examine the conditional maximum likelihood ...
Carroll, Raymond J., Spiegelman, Clifford H., Lan, K. K. Gordon, Bailey, Kent T., Abbott, Robert D.   +4 more
openaire   +1 more source

Identification of dynamic errors-in-variables models

Automatica, 1996
From the conclusion: ``The problem of identifying a causal linear dynamic system excited by a stationary zero-mean noise with unknown rational spectrum is considered for the case when the input-output measurements are corrupted by additive and uncorrelated noises of unknown rational spectra.'' The authors show that under mild conditions, the model is ...
Paolo Castaldi, Umberto Soverini
openaire   +2 more sources

A Note on an 'Errors in Variables' Model

Journal of the American Statistical Association, 1966
Abstract We consider an errors in variables model in which the ‘true’ part of the determining variable is generated by a simple forecasting mechanism. It is shown that the Least Squares errors in variables bias can be interpreted in terms of the parameters of the forecasting mechanism; and that the ‘standard’ result for this bias may no longer hold in ...
openaire   +1 more source