An Adaptive Distribution-Free Test for the Multi-Sample Lacation Problem

  • Song, Il-Seong (Department of Statistics, Sungshin Women's University, Seoul 132)
  • Published : 1984.06.01

Abstract

An adaptive distribution-free test is proposed for testing the equality of k independent distributions against unrestricted alternatives. In this paper, several rank-sum test statistics are considered as teh components of the adaptive one. The emprical powers of the adaptive testing procedure are compared to those of the classical F test and the component tests through a Monte Carlo study. The results show that the adaptive test has good power properties over a wide class of underlying distributions.

Keywords

References

  1. Ann. Math. Statist. v.25 Asymptotic Behavior of Some Rank Tests for Analysis of Variance Andrews, F.C.
  2. Theory of Rank Tests Hajek, J.;Sidak, Z
  3. J. Amer. Statist. Assoc. v.70 A Two-sample Adaptive Distribution-free Test Hogg, R.V.;Fisher, D.M.;Randles, R.H.
  4. J. Amer. Statist. Assoc. v.47 Use of Ranks in One Criterion Analysis of Variance Kruskal, W.H.;Wallis, W.A.
  5. Ann. Math. Statist. v.35 Asymptotic Efficiency of a Class of C-sample Tests Puri, M.L.
  6. Comm. of the A.C.M. v.15 An Approximate Method for Generating Symmetric Random Variables Ramberg, J.S.;Schmeiser, B.W.
  7. Comm. of the A.C.M. v.17 An Approximate Method for Generating Asymmetric Random Variables Ramberg, J.S.;Schmeiser, B.W.
  8. Comm. in Statist. v.2 no.4 Adaptive Distribution-Free Tests Randles, R.H.;Hogg, R.V.
  9. Introduction to the Theory of Nonparametric Statistics Randles, R.H.;Wolfe, D.A.
  10. J. Amer. Statist. Assoc. v.65 An Optimum Test Property of Two Known Statistics Uthoff, V.A.
  11. Ann. Statist. v.1 The Most Powerful Scale and Location Invariant Test of the Normal Versus Double Exponential Uthoff, V.A.