3.4 Information-Based Design
Traditional sample size calculation takes into account both the magnitude of the treatment
effect (
) and values of the nuisance parameter (e.g., the variance for continuous endpoints or the placebo response for binary endpoints), with the best guesses of the nuisance parameter used for the initial sample size calculation. However, if initial estimates of the nuisance parameters are incorrect, this can adversely impact the statistical power to detect a clinically meaningful difference, if indeed a treatment difference exists. One way of addressing this uncertainty around nuisance parameters is to utilize an information-based ...
) and values of the nuisance parameter (e.g., the variance for continuous endpoints or the placebo response for binary endpoints), with the best guesses of the nuisance parameter used for the initial sample size calculation. However, if initial estimates of the nuisance parameters are incorrect, this can adversely impact the statistical power to detect a clinically meaningful difference, if indeed a treatment difference exists. One way of addressing this uncertainty around nuisance parameters is to utilize an information-based ...Get Modern Approaches to Clinical Trials Using SAS: Classical, Adaptive, and Bayesian Methods now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
