Journal of Korean Society for Quality Management (품질경영학회지)

Korean Society for Quality Management (한국품질경영학회)
권호 표지

The Effect of Outliers in Regression Analysis

회귀 분석에서 이상치가 미치는 영향

  • Kim, Kwang-Soo (Dept. of Industrial Engineering, Chung Ju National University) ;
  • Bae, Young-Ju (Dept. of Industrial Engineering, Chung Ju National University) ;
  • Lee, Jin-Gue (Dept. of Industrial Engineering, Dongguk University)
  • 김광수 (충주산업대학교 산업공학과) ;
  • 배영주 (충주산업대학교 산업공학과) ;
  • 이진규 (동국대학교 산업공학과)
  • Published : 1996.06.20
Download PDF
⟨ Previous Next ⟩

Abstract

Outlier is one that appears to deviate extremely from other data in collected data. Thus treatment of outlier is very important work, because it is to distort the meaning of whole data in its analysis and to reduce the accuracy and validity for adequate models. The aim of this paper is to present some ways of handling outliers in given data and to investigate the effect of the analysis result before and after outlier reject. As a variety of methods has been proposed, we sellect the linear regression analysis and two linear programming techniques and compare to each result.

Keywords