Skip to main content

Some Improved Tests for Multivariate One-Sided Hypotheses

Abstract

Multivariate one-sided hypothesis-testing problems are very common in clinical trials with multiple endpoints. The likelihood ratio test (LRT) and union-intersection test (UIT) are widely used for testing such problems. It is argued that, for many important multivariate one-sided testing problems, the LRT and UIT fail to adapt to the presence of subregions of varying dimensionalities on the boundary of the null parameter space and thus give undesirable results. Several improved tests are proposed that do adapt to the varying dimensionalities and hence reflect the evidence provided by the data more accurately than the LRT and UIT. Moreover, the proposed tests are often less biased and more powerful than the LRT and UIT.

This is a preview of subscription content, access via your institution.

References

  1. Bloch DA, Lai TL, Tubert-Bitter P (2001) One-sided tests in clinical trials with multiple endpoints. Biometrics 57:1039–1047

    Article  PubMed  MathSciNet  Google Scholar 

  2. Hsu JC (1996) Multiple comparisions – theory and methods. Chapman and Hall, London

    Google Scholar 

  3. Murphy SA, Johnson LC, Wu L, Fan JJ, Lohan J (2003) Bereaved parents’ outcomes 4 to 60 months after their children’s deaths by accident, suicide, or homicide: a comparative study demonstrating differences. Death Stud 27:39–61

    Google Scholar 

  4. O’Brien PC (1984) Procedures for comparing samples with multiple endpoints. Biometrics 40:1079–1087

    PubMed  Article  MathSciNet  Google Scholar 

  5. Perlman MD (1969) One-sided testing problems in multivariate analysis. Ann Stat 40:549–567

    Article  MathSciNet  Google Scholar 

  6. Perlman MD, Wu L (1999) The Emperor’s new tests (with discussion). Stat Sci 14:355–381

    MATH  MathSciNet  Google Scholar 

  7. Perlman MD, Wu L (2003) On the validity of the likelihood ratio and maximum likelihood methods. J Stat Plan Inf 117:59–81

    Article  MATH  MathSciNet  Google Scholar 

  8. Perlman MD, Wu L (2004) A note on one-sided tests with multiple endpoints. Biometrics 60:276–280

    Article  PubMed  MathSciNet  MATH  Google Scholar 

  9. Robertson T, Wright FT, Dykstra RL (1988) Order-restricted statistical inference. Wiley, New York

    MATH  Google Scholar 

  10. Shimodaira H (2000) Approximately unbiased one-sided tests of the maximum of normal means using iterated bootstrap corrections. Technical report no. 2000–07, Department of Statistics, Stanford University, Stanford

    Google Scholar 

  11. Shimodaira, Hasegawa (1999) Multiple comparisons of log-likelihoods with applications to phylogenetic inference. Mol Biol Evol 16:1114–1116

    Google Scholar 

  12. Tamhane AC, Logan BR (2004) A superiority-equivalence approach to one-sided tests on multiple endpoints in clinical trials. Biometrika 91:715–727

    Article  MATH  MathSciNet  Google Scholar 

  13. Tang D-I (1994) Uniformly more powerful tests in a one-sided multivariate problem. J Am Stat Assoc 89:1006–1011

    MATH  Article  Google Scholar 

  14. Wollan PC, Dykstra RL (1987) Algorithm AS 225. Appl Stat 36: 234–240

    MATH  Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Michael D. Perlman.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Perlman, M.D., Wu, L. Some Improved Tests for Multivariate One-Sided Hypotheses. Metrika 64, 23–39 (2006). https://doi.org/10.1007/s00184-006-0028-0

Download citation

Keywords

  • One-sided hypothesis
  • Multiple endpoints
  • Likelihood ratio test
  • Union-intersection test
  • p-value