Prediction in polynomial errors-in-variables models

Bootstrapping Errors-in-Variables Models

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 derivations. In many computer vision tasks a reg...

Errors in Variables in Simultaneous Equation Models

Testing the Suitability of Polynomial Models in Errors - in - Variables Problems

A low-degree polynomial model for a response curve is used commonly in practice. It generally incorporates a linear or quadratic function of the covariate. In this paper we suggest methods for testing the goodness of fit of a general polynomial model when there are errors in the covariates. There, the true covariates are not directly observed, and conventional bootstrap methods for testing are ...

Testing the Suitability of Polynomial Models in Errors-in-variables Problems by Peter Hall

A low-degree polynomial model for a response curve is used commonly in practice. It generally incorporates a linear or quadratic function of the covariate. In this paper we suggest methods for testing the goodness of fit of a general polynomial model when there are errors in the covariates. There, the true covariates are not directly observed, and conventional bootstrap methods for testing are ...

Efficient Estimation of Errors-in-Variables Models

The paper addresses the discrete-time linear process identification problem assuming noisy input and output records available for the parameter estimation. The efficient algorithms are derived for the simultaneous estimation of the process and noise parameters. Implementation techniques based on matrix and polynomial decompositions are given in details resulting in estimation algorithms with re...