한국경영과학회지 (Journal of the Korean Operations Research and Management Science Society)

  • 제21권1호
  • /
  • Pages.163-170
  • /
  • 1996
  • /
  • 1225-1119(pISSN)
  • /
  • 2733-4759(eISSN)
한국경영과학회 (The Korean Operations Research and Management Science Society)
권호 표지

Applicability of the Ordinary Least Squares Procedure When Both Variables are Subject to Error

  • Kim, Kil-Soo (Department of Industrial Engineering, KAIST) ;
  • Byun, Jai-Hyun (Department of Industrial Engineering, Gyeongsang National University) ;
  • Yum, Bong-Jin (Department of Industrial Engineering, KAIST)
  • 발행 : 1996.04.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

An errors-in-variables model (EVM) differs from the classical regression model in that in the former the independent variable is also subject to error. This paper shows that to assess the applicability of the ordinary least squares (OLS) estimation procedure to the EVM, the relative dispersion of the independent variable to its error variance must be also considered in addition to Mandel's criterion. The effect of physically reducing the variance of errors in the independent variable on the performance of the OLS slope estimator is also discussed.

키워드

참고문헌

  1. Measurement Error Models Fuller,W.A.
  2. The Advanced Theroy of Statistics v.2 Kendall,M.G.;A.Stvart
  3. J. Ame. Statist. v.54 The Fitting of Straight Lines When Both Variables Are Subject to Error Madansky,A.
  4. J. Quality Technology v.16 Fitting Straight Lines When Both Variables Are Subject to Error Mandel,J.
  5. J. Multivariate Analysis v.1 Estimating Structural and Functional Relationships Moran,P.A.P.
  6. J. Amer. Statist. Ass. v.65 Least Square are Grouping Method Estimators in the Errors in the Variables Model Richardson,D.H.;D.Wu
  7. Comm. Statist-Theor. Meth. v.14 Asymptotic Properties of the OLS and GRLS Estimator for the Replicated Functional Relationship Model Yum,B.J.