A New Method for Detection and Estimation of Outliers in Multiple Linear Regression Model

  IJCTT-book-cover
 
International Journal of Computer Trends and Technology (IJCTT)          
 
© 2015 by IJCTT Journal
Volume-29 Number-3
Year of Publication : 2015
Authors : Dr. Nabeel George Nacy, Dr.Ghazi. I .Raho, Zrean Salam Ahmed
  10.14445/22312803/IJCTT-V29P121

MLA

Dr. Nabeel George Nacy, Dr.Ghazi. I .Raho, Zrean Salam Ahmed "A New Method for Detection and Estimation of Outliers in Multiple Linear Regression Model". International Journal of Computer Trends and Technology (IJCTT) V29(3):120-128, November 2015. ISSN:2231-2803. www.ijcttjournal.org. Published by Seventh Sense Research Group.

Abstract -
This paper aims to suggest a new method to detect outliers in multiple linear regression model and suggest three new methods to estimating this outliers. The suggested new method to detect outliers depending on the statistic DFSTAT proposed by Beasley et al. (1980) and modified the ellipse equation which proposed by Nacy (2001) and it also suggest three new methods to estimating these outliers according to the methods proposed by Nacy (2001) after modifying.

References
[1] Akter, S. & Khan, M. H. (2010) “ Multiple-Case Outlier Detection in Multiple Linear Regression Model Using Quantum - Inspired Evolutionary Algorithm” COMPUTERS, Vol. 5, no. 12, p.p. 1779 – 1788.
[2] Belsley, D. A. ,Kuh, E. &Welsch, R. E. (1980) “ Regression Diagnostics Identifying Influential Data and Sources of Collinearity ” , John Wiley, New York.
[3] Billor, N. &Kiral, G. (2008) “A Comparison of Multiple Outlier Detection Methods for Regression Data”Communications in Statistics—Simulation and Computation, no. 37, p.p. 521-545.
[4] Chatterjee, s. &Hadi, A. S. (1988), “ Sensitivity Analysis in linear Regression ” John Wiley, New York, p. p. (129, 95, 96).
[5] Hu, Y. (2011) “linear regression”Journal of Validation technology, Spring 2011, p.p. 15–22.
[6] Rousseuw, P. J. &Leroy, A. M. (1987) “ Robust Regression and Outliers Detection” John Wiley, Ney York.
[7] Raho,Ghazi &nor Burhan (2001) Management information system computerization

Keywords
Belsely Nacy , multiple linear regression models , detecting outliers , estimating outliers.