Comparison of some robust methods in the presence of problems of multicollinearity and high leverage points
DOI:
https://doi.org/10.33095/jeas.v25i114.1749Keywords:
الانحدار الخطي المتعدد، تعدد العلاقة الخطية، نقاط الانعطاف العالية، مقدر MM ، مقدر GM2، انحدار الحرف للـ جاكنايف ., Multiple Linear Regression , Multicollinearity, high leverage point, Jackknife ridge regression, MM-estimator, GM2-estimator.Abstract
Abstract
The multiple linear regression model of the important regression models used in the analysis for different fields of science Such as business, economics, medicine and social sciences high in data has undesirable effects on analysis results . The multicollinearity is a major problem in multiple linear regression. In its simplest state, it leads to the departure of the model parameter that is capable of its scientific properties, Also there is an important problem in regression analysis is the presence of high leverage points in the data have undesirable effects on the results of the analysis , In this research , we present some of the robust methods in the multiple linear regression model These methods include the (Jackknife Ridge regression) methods based on the (MM) estimator and the (GM2) estimator (Modified Generalized M-estimator) . Using the Monte Carlo simulation, the two methods were compared in accordance with the comparison criterion, the mean squares error (MSE) and sample sizes (n = 20, n = 50, n = 100) and different pollution ratios (τ = 5%, 15%) , The comparison shows that (RJGM2) is the best method for estimating the parameters of the multiple linear regression model, which has the lowest value for mean squares error (MSE) compared with the rest of the other estimations.
Downloads
Published
Issue
Section
License
Articles submitted to the journal should not have been published before in their current or substantially similar form or be under consideration for publication with another journal. Please see JEAS originality guidelines for details. Use this in conjunction with the points below about references, before submission i.e. always attribute clearly using either indented text or quote marks as well as making use of the preferred Harvard style of formatting. Authors submitting articles for publication warrant that the work is not an infringement of any existing copyright and will indemnify the publisher against any breach of such warranty. For ease of dissemination and to ensure proper policing of use, papers and contributions become the legal copyright of the publisher unless otherwise agreed.
The editor may make use of Turnitin software for checking the originality of submissions received.
