Journal of applied mathematics & informatics

The Korean Society for Computational and Applied Mathematics (한국전산응용수학회)
권호 표지

A STUDY ON A NONPARAMETRIC TEST FOR THE PARALLELISM OF k REGRESSION LINES AGAINST ORDERED ALTERNATIVES

  • Jee, Eun-Sook (Department of Mathematics, College of Science, Kwangwoon University)
  • Published : 2001.05.01

⟨ Previous Next ⟩

Abstract

In this paper a nonparametric test for the parallelism of k regression lines against ordered alternatives, when the independent variables are positive and all regression lines have a common intercept is proposed. The proposed test is based on a Jonckheere-type statistic applied to residuals. Under some conditions the proposed test statistic is asymptotically distribution-free. The small-sample powers of our test are compared with other tests by a Monte Carlo study. The simulation results show that the proposed test has significantly higher empirical powers than the other tests considered in this paper.

Keywords

References

  1. Communication in Statistics-Theory and Methods v.A5 no.11 Testing Parallelism of Regression Lines against Ordered Alternatives Adichie,J.N.
  2. Theory and Application of Isotonic Regression Statistical Inference under Order Restrictions Barlow,R.E.;Bartholomew,D.J.;Bremner,J.M.;Brunk,H.D.
  3. Biometrika v.46 A Test of Homogeneity for Ordered Alternatives Bartholomew,D.J.
  4. The Annals of Mathematical Statistics v.34 Testing Homogeneity against Ordered Alternatives Chacko,V.J.
  5. Biometrika v.41 A Distribution-Free k-Sample Test Against Ordered Alternatives Jonckheere,A.R.
  6. Journal of the American Statistical Association v.73 A Small-Sample Comparison of Rank Score Tests for Parallelism of Several Regression Lines Lo,L.C.;Simkin,M.G.;Worthley,R.G.
  7. The Annals of Statistics v.10 On the Asymptotic Normality of Statistics with Estimated Parameters Randles,R.H.
  8. Journal of the American Statistical Association v.79 On Tests Applied to Residuals Randles,R.H.
  9. Mathematische Operationsforschung und Statistik Series Statistics v.15 Testing Concurrence and Parallelism of Several Sample Regressions against Ordered Alternatives Rao,K.S.M.;Gore,A.P.
  10. Technical Report, Department of Statistics, Ohio State University Distribution-Free Tests for Equality of Several Regression Equations Smith,T.M;Wolfe,D.A.