Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지

Predictive Probabilities for New Patients.

  • Daehyun Chung (Department of Statistics, Chungbuk National University, Cheongju, Chungbuk, 320-763., KOREA)
  • Published : 1995.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

Under the certain assumptions, we derive the recursive formula for the predictive probabilities that a new patient will survive up to the time, conditional on the data. The formula for a new patient is extended to obtain the computational algorithms for the predictive probabilties for several new patients. We correct Genest and Kalbfleisch's approach for several new patients, since we find that their approach is incorrect.

Keywords

References

  1. Journal of the American Statistical Association v.83 Bayesian Nonparametric Survival Analysis Berliner,L.M.;Hill,B.M.
  2. Canadian Journal of Statistics v.12 Predicting Pareto and Exponential Observables Geisser,S.
  3. Journal of the American Statistical Association v.83 Comment on Berliner and Hill Genest,C.;Kalbfleisch,J.
  4. Journal of the American Statistical Association v.63 Posterior Distribution of Percentile: Bayes Theorem for Sampling from a Finite Popluation Hill,B.M.
  5. Journal of the American Statistical Association v.53 Nonparametric Estimation from Incomplete Observations Kaplan,E.L.;Meier,P.
  6. Annals of Statistics v.16 Diffuse Models for Sampling and Predictive Inference Lane,D.;Sudderth,W.
  7. Statistical Methods for Survival Data Analysis Lee,E.T.