Corresponding between Error Probabilities and Bayesian Wrong Decision Lasses in Flexible Two-stage Plans

  • Ko, Seoung-gon (Department of Applied Statistics, Kyungwon University)
  • Published : 2000.12.01

Abstract

Ko(1998, 1999) proposed certain flexible two-stage plans that could be served as one-step interim analysis in on-going clinical trials. The proposed Plans are optimal simultaneously in both a Bayes and a Neyman-Pearson sense. The Neyman-Pearson interpretation is that average expected sample size is being minimized, subject just to the two overall error rates $\alpha$ and $\beta$, respectively of first and second kind. The Bayes interpretation is that Bayes risk, involving both sampling cost and wrong decision losses, is being minimized. An example of this correspondence are given by using a binomial setting.

Keywords

References

  1. Biometrics v.35 Improced Graphs for Calculating Sample Sizes when Comparing Two Independent Binomial Distributions Aleong J.;Bartlett, D.E.
  2. Statistics in Medicine v.10 Interim analysis in clinical trials Armitage, P.
  3. Biometrics v.34 An Improved Approximate Formula for Calculating Sample Sizes for Comparing Two Binomial Distributions Casagrande, J.T.;Pike, M.C.
  4. Journal of the American Statistical Association v.71 Two-stage plans compared with fixed-sample size and Wald SPRT plans Colton, T.;McPherson, K.
  5. Biometrics v.34 A Graphical Aid for Determining Sample Size when Comparing two Independent Proportions Felgl, P.
  6. The Korean Communications in Statistics v.5 no.1 Hybrid Group-sequential Conditional-Bayes Approaches to the Double Sampling Plans Ko, S.G.
  7. The Korean Communications in Statistics v.6 no.1 Adjusting Practical aims in Optimal Extended Double Sampling Plans Ko, S.G.
  8. 1st edtion Testing Statistical Hypotheses Lehmann, E. L.
  9. Biometrics v.35 A multiple testing procedure for clinical trials O'Brien, P.C.;Fleming, T. R.
  10. Linear Programming with Statistical Applications Sposito, V.A.