Therapeutic Equivalence Using a Rich Family of Prior Distributions
Therapeutic Equivalence in some contexts occurs when functions of parameters such as differences or ratios lie within some specified confidence region. A specific class of parametric discrepancy measures is examined. One then applies the Bayesian neighborhood null hypothesis theory to derive posterior confidence regions on these measures. Data from a leukemia clinical trial is used to demonstrate conditions under which equivalent survival benefit of two treatments is achieved. All results are derived numerically with conditions under which the posterior distributions approximate standard F-ratios. The achieved goal is that of establishing therapeutic equivalence using a rich family of prior distributions.
KeywordsPrior Distribution Posterior Density Under Sampling Rich Family Prior Structure
Unable to display preview. Download preview PDF.
- Bartolucci, A. A. and Singh, K. P. (1993), “Therapeutic Equivalence - A Bayesian Approach,” ASA Proceedings of the Midwest Biopharmaceutical Statistics Workshop, Muncie, Indiana, May 19–21, 1993. An Invited Paper. 349–357Google Scholar
- Dickey, J. M. (1979), “Beliefs about Beliefs, a Theory for Statistical Assessments of Subjective Probabilities,” In Bayesian Statistics, (ed. by J. Bernardo).,University of Valencia Press. Spain.Google Scholar
- Glatstein, E. and Makuch, R. W. (1984), “Illusion and Reality: Practical Pitfalls in Interpreting Clinical Trials,” Journal of Clinical Oncology, 2, 488–497.Google Scholar
- Raiffa, H. and Schlaifer, R. (1961). Applied Statistical Decision Theory, M. I. T. Press. Cambridge, Massachusetts.Google Scholar
- Schuirmann, D. J. (1987), “A Comparison of the Two One-sided Tests Procedure and the Power Approach for Assessing the Equivalence of Average Bioavailability,” Journal of Pharmacokinetics and Biopharmaceutics, 6, 657–680.Google Scholar