Asymptotic Normality of LS Estimate in Simple Linear EV Regression Model

Abstract

Though EV model is theoretically more appropriate for applications in which measurement errors exist, people are still more inclined to use the ordinary regression models and the traditional LS method owing to the difficulties of statistical inference and computation. So it is meaningful to study the performance of LS estimate in EV model. In this article we obtain general conditions guaranteeing the asymptotic normality of the estimates of regression coefficients in the linear EV model. It is noticeable that the result is in some way different from the corresponding result in the ordinary regression model.

Keywords

EV model / LS estimate / Asymptotic normality / 62E20 / 62J05

References

[1] Drygas Z. Wahrsch. verw. Gebiete, 1976, 34: 1

[2] Lai J. Multivariate Anal., 1979, 9: 343

[3] Anderson Ann. Statist., 1984, 12: 1

[4] Cui Sys. Sci. and Math. Sci., 1997, 10: 225

[5] Fuller, W. A., Measurement Error Models, John Wiley & Sons, New York, 1987.

[6] Liu Acta Math. Sci., 2005, 25B: 50