Theory of Probability and Mathematical Statistics
CONSISTENCY OF ORTHOGONAL REGRESSION ESTIMATOR IN IMPLICIT LINEAR ERRORS-IN-VARIABLES MODEL
O. O. Dashkov, A. G. Kukush
Download PDF
Abstract: An implicit linear errors-in-variables model is considered, where the true points belong to a hyperplane in a Euclidean space and the total error variance-covariance matrix is proportional to the identity matrix. The orthogonal regression estimator of the hyperplane is studied. Sufficient conditions for the consistency and strong consistency of the estimator are presented. The results are applied to an explicit multiple errors-in-variables model with intercept.
Keywords: Consistent estimator, errors-in-variables model, implicit linear regression, multiple linear regression, orthogonal regression, total least squares
Bibliography: 1. W. Fuller, Measurement error models, Wiley, New York, 1987.
2. P. Gallo, Consistency of regression estimates when some variables are subject to errors, Comm. Statist. Theory Methods, 11 (1982), no. 9, 973-983.
3. L. J. Gleser, Estimation in multivariate errors-in-variables regression model: large sample results, Ann. Statist., 9 (1981), no. 1, 24-44.
4. A. I. Kostrikin, Yu. I. Manin, Linear Algebra and Geometry, Series in Algebra, Logic and Applications, vol. 1, CRC Press, 1989.
5. A. Kukush, S. Van Huel, Consistency of elementwise-weighted total lest squares estimator in a mulivariate errors-in-variables model AX = B, Metrika, 59 (2004), no. 1, 75-97.
6. S. V. Masiuk, A. G. Kukush, S. V. Shklyar, M. I. Chepurny, I. A. Likhtarov (ed.), Radiation risk estimation: Based on measurement error models, 2nd ed., De Gruyter Ser. Math. Life Sci., vol. 5, De Gruyter, 2017.
7. S. V. Shklyar, Conditions for the consistency of the total least squares estimator in an errors-in-variables linear regression model, Theory Probab. Math. Statist., 83 (2011), 175-190.
