Convergence of Score process in the Cox Proportional Hazards Model

  • Hwang, Jin-Soo (Department of Statistics, Inha University, Inchon, 402-751)
  • Published : 1997.03.01

Abstract

We study the asymptotic behavior of the maximum partial likelihood estimator in the Cox proportional hazards model in the presence of nuisance parameters when the entry of patients is staggered. When entry of patients is simultaneous and there is only one regression parameter in the Cox model, the efficient score process of the partial likelihood is martingale and converges weakly to a time-chnaged Brownian motion. Our problem is to get a similar result in the presence of nuisance parameters when entry of patient is staggered.

Keywords

References

  1. Convergence of Probability Measures Billingsley, P.
  2. Journal of Royal Statistical Society Series B v.34 Regression Models and life tables(with discussion) Cox, D.R.
  3. Biometrika v.62 Partial Likelihood Cox, D.R.
  4. Annals of Probability v.3 On tail probabilities for martingales Freedman, D.
  5. Mathematisch Centrum v.124 Censoring and Stochastic Integrals Gill, R.
  6. Annals of Statisticals v.11 Sequential sampling based on observed Fisher information to gurantee the accuracy of the maximum likelihood estimator Grambsch, P.
  7. Bulletin of the Institute for Basic Science v.16 On uniform Consistency of Cox-Regression parameter Hwang, J.S.
  8. Bulletin of the Institute for Basic Science Uniform asymptotic equipvalence between observed Fisher information number and expected Fisher information number Hwang, J.S.
  9. Annals of Statistics v.11 Fixed accuracy estimation of a autoregressive parameters Lai, T.L.;Siegmund, D.O.
  10. Zeitschrift fur Wahrscheinlichkeitstheorie und Verwandt Gebiete v.51 Central limit theorem for local martingales Rebolledo, R.
  11. Biometrika v.70 Sequential Analysis of the proportional hazards model Sellke;Siegmund, D.O.