Lifetime Data Analysis

, Volume 10, Issue 4, pp 389–405

Comparisons of Test Statistics Arising from Marginal Analyses of Multivariate Survival Data

Article

Abstract

We investigate the properties of several statistical tests for comparing treatment groups with respect to multivariate survival data, based on the marginal analysis approach introduced by Wei, Lin and Weissfeld [‘‘Regression Analysis of multivariate incomplete failure time data by modelling marginal distributians,’’ JASA vol. 84 pp. 1065–1073]. We consider two types of directional tests, based on a constrained maximization and on linear combinations of the unconstrained maximizer of the working likelihood function, and the omnibus test arising from the same working likelihood. The directional tests are members of a larger class of tests, from which an asymptotically optimal test can be found. We compare the asymptotic powers of the tests under general contiguous alternatives for a variety of settings, and also consider the choice of the number of survival times to include in the multivariate outcome. We illustrate the results with simulations and with the results from a clinical trial examining recurring opportunistic infections in persons with HIV.

Keywords

directional tests marginal model multivariate survival data omnibus test recurring events 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Andersen, P.K., Gill, R.D. 1981Cox’s regression model for counting processes: A large sample studyThe Annals of Statistics1011001120Google Scholar
  2. Cai, J., Prentice, R.L. 1995Estimating equations for hazard ratio parameters based on correlated failure time dataBiometrika82151164Google Scholar
  3. R. J. Cook, J. F. Lawless, and C. Nadeau, ‘‘Robust tests for treatment comparisons based on recurrent event responses’’, Technical Report vol. 40 1995.Google Scholar
  4. Cox, D.R. 1972Regression models and life tablesJournal of Royal Statististical Society B34187220Google Scholar
  5. Dolin, R., Amato, D.A., Fischl, M.A.,  et al. 1995Zidovudine compared with didanosine in patients with advanced HIV type 1 infection and little or no previous experience with zidovudineArchives of Internal Medicine155961974Google Scholar
  6. Hauser, W.A., Rich. J., S.S., Lee, R.-J., Annegers, J.F., Anderson, V.E. 1998Risk of recurrent seizures after two unprovoked seizuresNew England Journal of Medicine338429434Google Scholar
  7. Hughes, M. 1997Power considerations for clinical trials using multivariate time to event dataStatistical in Medicine16865882Google Scholar
  8. Kahn, J., Lagakos, S.W., Richman, D.D., Cross, A.,  et al. 1992A controlled trial comparing continued zidovudine with didanosine in human immunodeficiency virus infectionNew England Journal of Medicine327581587Google Scholar
  9. Q. H. Li, The Relationship between Directional and Omnibus Tests for a Vector Parameter, Doctoral Thesis, Department of Biostatistics, Harvard University, 1997.Google Scholar
  10. Liang, K.Y., Self, S.G., Chang, Y.C. 1993Modeling marginal hazards in multivariate failure time dataJournal of Royal Statistical Society B55441453Google Scholar
  11. Lin, D.Y. 1994Cox regression of multivariate failure time data: The marginal approachStatistical in Medicine1322332247Google Scholar
  12. Lin, J.S., Wei, L.J. 1992Linear regression analysis for multivariate failure time observationsJASA8710911097Google Scholar
  13. Prentice, R.L., Williams, B.J., Peterson, A.V. 1981On the regression analysis of multivariate failure time DataBiometrika68373379Google Scholar
  14. Richman, D., Grimes, J., Lagakos, S. 1990Effect of stage of disease and drug dose on zidovudine susceptibilities of isolates of human immunodeficiency virusJournal of Acquired Immune Deficiency Syndromes3743746Google Scholar
  15. Wei, L.J., Lin, D.Y., Weissfeld, L. 1989Regression analysis of multivariate incomplete failure time data by modeling marginal distributionsJASA8410651073Google Scholar
  16. Yang, Y., Ying, Z. 2001Marginal proportional hazards models for multipleevent-time dataBiometrika88581586Google Scholar

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  1. 1.Center for Drug Evaluation and Research, Food and Drug AdministrationRockvilleUSA
  2. 2.Department of BiostatisticsHarvard School of Public HealthBostonUSA

Personalised recommendations