Annals of the Institute of Statistical Mathematics

, Volume 63, Issue 6, pp 1141–1163 | Cite as

An optimal approach for hypothesis testing in the presence of incomplete data

Article

Abstract

The adverse effect of small sample sizes, excessive nonresponse rate, and high dimensionality on likelihood ratio test statistic can be reduced by integrating with respect to a prior distribution. If information regarding the prior is too general (for example, only a parametric family can be specified), this distribution can be chosen from a principle of the most powerful testing. We propose the integrated most powerful test in the presence of missing data. This test can be used as a viable alternative to the maximum likelihood.

Keywords

Parametric hypothesis testing Most powerful test Likelihood ratio Missing data Maximum likelihood 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Choi S., Hall W.J., Schick A. (1996) Asymptotically uniformly most powerfull tests in parametric and semiparametric models. The Annals of Statistics 24: 841–861MathSciNetMATHCrossRefGoogle Scholar
  2. Efron B., Tibshirani J. (1993) An introduction to the bootstrap. Chapman & Hall, New York, p 436MATHGoogle Scholar
  3. Goeman J.J., Van De Geer S.A., Van Houwelingen H.C. (2006) Testing against a high dimensional alternative. Journal of the Royal Statistical Society B 68: 477–493MATHCrossRefGoogle Scholar
  4. Krieger A.M., Pollak M., Benjamin Y. (2003) Surveillance of a simple linear regression. Journal of the Americal Statistical Association 98: 456–469MATHCrossRefGoogle Scholar
  5. Laud P., Ibrahim J. (1995) Predictive model selection. Journal of the Royal Statistical Society B 57: 247–262MathSciNetMATHGoogle Scholar
  6. Lehmann E.L. (1986) Testing statistical hypotheses. Springer, New YorkMATHGoogle Scholar
  7. Little R.J.A., Rubin D.B. (2002) Statistical analysis with missing data. New Jersey, Wiley-InterscienceMATHGoogle Scholar
  8. Lorden G. (1967) Integrated risk of asymptotically Bayes sequential tests. The Annals of Mathematical Statistics 38: 1399–1422MathSciNetMATHCrossRefGoogle Scholar
  9. Marden J.I. (2000) Hypothesis testing: From p values to Bayes factors. Journal of the Americal Statistical Association 95: 1316–1320MathSciNetMATHCrossRefGoogle Scholar
  10. Pollak M. (1978) Optimality and almost optimality of mixture stopping rules. The Annals of Statistics 6: 910–916MathSciNetMATHCrossRefGoogle Scholar
  11. Yakir B. (1998) On the average run length to false alarm in surveillance problems which possess an invariant structure. The Annals of Statistics 26: 1198–1214MathSciNetMATHCrossRefGoogle Scholar

Copyright information

© The Institute of Statistical Mathematics, Tokyo 2010

Authors and Affiliations

  1. 1.Department of BiostatisticsThe State University of New York at BuffaloBuffaloUSA
  2. 2.Division of BiostatisticsMedical College of WisconsinMilwaukeeUSA

Personalised recommendations