Data validation with unknown variance matrix
نویسندگان
چکیده
The data validation consists in obtaining an estimation of the true values of process variables that respect the balance equations. Generally, the procedure needs the knowledge of the variance of the measurement errors; unfortunately, in most situations, we only have a rough estimation of this variance and therefore the data validation procedure gives results depending on this poor estimation. A pioneer work of Almasy and Mah (1984) presents a solution to this problem based on the analysis of the constraint residuals. Darouach et al. (1989) developed a slighty different approach based on a maximum likelihhod estimator. Here we present a direct method that simultaneously estimates the variances of the measurement errors and reconciles the data with respect to the balance equations. Some numerical results illustrate the efficiency of the proposed method.
منابع مشابه
Iterative generalized cross-validation for fusing heteroscedastic data of inverse ill-posed problems
S U M M A R Y The method of generalized cross-validation (GCV) has been widely used to determine the regularization parameter, because the criterion minimizes the average predicted residuals of measured data and depends solely on data. The data-driven advantage is valid only if the variance–covariance matrix of the data can be represented as the product of a given positive definite matrix and a...
متن کاملLarge-scale Inversion of Magnetic Data Using Golub-Kahan Bidiagonalization with Truncated Generalized Cross Validation for Regularization Parameter Estimation
In this paper a fast method for large-scale sparse inversion of magnetic data is considered. The L1-norm stabilizer is used to generate models with sharp and distinct interfaces. To deal with the non-linearity introduced by the L1-norm, a model-space iteratively reweighted least squares algorithm is used. The original model matrix is factorized using the Golub-Kahan bidiagonalization that proje...
متن کاملA numerical Algorithm Based on Chebyshev Polynomials for Solving some Inverse Source Problems
In this paper, two inverse problems of determining an unknown source term in a parabolic equation are considered. First, the unknown source term is estimated in the form of a combination of Chebyshev functions. Then, a numerical algorithm based on Chebyshev polynomials is presented for obtaining the solution of the problem. For solving the problem, the operational matrices of int...
متن کاملBias and variance of validation methods for function approximation neural networks under conditions of sparse data
Neural networks must be constructed and validated with strong empirical dependence, which is difficult under conditions of sparse data. This paper examines the most common methods of neural network validation along with several general validation methods from the statistical resampling literature as applied to function approximation networks with small sample sizes. It is shown that an increase...
متن کاملAn Augmented Classical Least Squares Method for Quantitative Raman Spectral Analysis against Component Information Loss
We propose an augmented classical least squares (ACLS) calibration method for quantitative Raman spectral analysis against component information loss. The Raman spectral signals with low analyte concentration correlations were selected and used as the substitutes for unknown quantitative component information during the CLS calibration procedure. The number of selected signals was determined by...
متن کامل