On Testing Monotonicity of Mean Residual Life from Randomly Censored Data

  • Published : 1996.10.31

Abstract

This paper proposes a new nonparametric test for testing the null hypothesis that the MRL is constant against the alternative hypothesis that the MRL is decreasing (increasing) for ramdomly censored data. The proposed test statistic is a L-statistic, and we use L-statistic theory to establish its asymptotic normality of the test statistic. We discuss the efficiency loss due to censoring and also calculate the asymptotic relative efficiencies of our test statistic with respect to the Chen, Hollander and Langberg's test for several alternatives.

Keywords

References

  1. J. Amer. Statistical Assoc. v.64 Some criteria for aging Bryson, M.C.;Siddiqui, M.M.
  2. Mean residual life. Theory and applications;Handbook of Statistics, vol. 7, Reliability and Quality Control Guess, F.;Proschan, F.;Krishnaiah, P.R.(ed.);Rao, C.R.(ed.)
  3. Biometrika v.62 Test for the mean residual life Hollander, M.;Proschan, F.
  4. Biometrics v.39 Tests for monotone mean residual life, using randomly censored data Chen, Y.Y.;Hollander, M.;Langberg, N.A.
  5. Journal of Statistical Planning and Inferences v.21 A family of test statis-tics for detecting monotonic mean residual life Bergman, B.;Klesfjo, B.
  6. Scand. J. Statistics v.17 Test for monotonicity properties of the mean residual life function Aly, E.A.A.
  7. Biometrika v.79 A new test for mean residual life time Ahmad, I.A.
  8. J. Nonparametric Statistics v.3 Test for DMRL using censored data Lim, J.H.;Park, D.H.
  9. J. Amer. Statistical Assoc. v.53 Nonparametric estimation from incomplete observations Kaplan, E.L.;Meier, P.
  10. Testing whether mean residual life changes trend Guess, F.
  11. Percentile residual life functions - properties, testing and estimation Joe, H.
  12. Approximation Theorems of Mathematical Statistics Serfling, R.J.