Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지

On Alternative Collinearity Diagnostics in Linear MEM

  • Moon, Myung-Sang (Assistant Professor, Department of Statistics, Yonsei University)
  • Published : 1996.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

Collinearities contained in MEM cause the same problems as they do in traditional regression model, so the detection of collinearities is a crucial topic in MEM. One diagnostic was introduced by Carrillo-Gamboa and Gunst, but their method did not work in some cases. Two alternative collinearity diagnostics that provide reasonable measure of collinearities are proposed. Simulation study is performed to compare the small-sample properties of the proposed collinearity diagnostics.

Keywords

References

  1. The American Statistician v.39 What should be done when an estimated between-group covariance matrix is not nonnegative definite Amemiya, Y.
  2. Regression Diagnostics: Identifying Influential Data and Sources of Multicollinearity Belsley, D. A.;Kuh, E.;Welsch, R. E.
  3. Technometrics v.34 no.4 Measurement-Eroor-Model Collinearities Carrillo-Gamboa O.;Gunst R. F.
  4. Measurement error models Fuller, W. A.
  5. Communications in Statistics-Theory and Methods v.12 Regression analysis with multicollinear predictor variables: Definition, detection, and effects Gunst, R. F.
  6. Journal of Marketing Research v.19 Multicollinearity in structural equation models with unobservable variables Jagpal, H. S.
  7. Journal of the Royal Statistical Society, Series B v.31 Multicollinearity and Imprecise Estimation Silyvey, S. D.