Asymptotic Distribution of a Nonparametric Multivariate Test Statistic for Independence

  • Um, Yong-Hwan (Division of Computer Science, Sungkyul University)
  • Published : 2001.04.30

Abstract

A multivariate statistic based on interdirection is proposed for detecting dependence among many vectors. The asymptotic distribution of the proposed statistic is derived under the null hypothesis of independence. Also we find the asymptotic distribution under the alternatives contiguous to the null hypothesis, which is needed for later use of computing relative efficiencies.

References

  1. Journal of American Statistical Association v.92 Nonparametric on independence between two vectors Geiser, P.W.;Randles, R.H.
  2. Annals of Mathematical Statistics v.27 On the power of certain tests for independence in bivariate population Konijin, H.S.
  3. Journal of the American Statistical Association v.84 A distribution-free multivariate sign test based on inter-directions Randles, R.H.
  4. Academic Press Theory of Rank Tests Hajek, J.;Sidak, Z.
  5. Aspects of Multivariate Satistical Theory Muirhead, R.J.