Weighted Evidence Approach to Evaluation of Bridging Studies
- 2011-03-28 (Mon.), 10:30 AM
- Recreation Hall, 2F, Institute of Statistical Science
- Prof. Hsiao-Hui Sophie Tsou
- Institute of Population Health Sciences, National Health Research Institutes
Abstract
A bridging study defined by ICH E5 is usually conducted in a new region after a test product has been approved for commercial marketing in an original region due to its proven efficacy and safety. With the bridging study, the original clinical data are allowed to be extrapolated to the new bridging region. The conventional non-inferiority criterion requires the drug’s effect attained in the new region preserves a pre-specified proportion of the treatment effect attained in the original region. Such a criterion, however, is often impractical. In this presentation, we consider the overall treatment effect by combining the weighted effects attained in the original and bridging regions to evaluate the treatment effect in the bridging study. The proposed approach is an extension of weighted Z-test proposed by Lan et al (2005). We further propose an estimation approach to estimate the minimum weight required for the treatment effect of the local bridging region. Sample size required for the bridging region is determined based the proposed method. The simulation results of type I error rate and power for the weighted evidence approach are reported. An example is given to illustrate the application of the proposed procedures.