2
Faculty of mathematics, Semnan university, Semnan, Iran.
Abstract
The method of least squares is a very simple, practical and useful approach for estimating regression coefficients of the linear models. This statistical method is used by users of different fields to provide the best unbiased linear estimator with the least variance. Unfortunately, this method will not have reliable output if outliers are present in the dataset, as the collapse point (estimator consistency criterion) of this method is 0%. It is therefore important to identify these observations. Until now, the various methods have been proposed to identify these observations. In this article, the proposed methods are reviewed and discussed in details. Finally, by presenting a simulation example, we examine each of the proposed methods.
