The package ThreeArmedTrials provides functions for designing and analyzing non-inferiority or superiority trials with an active and a placebo control. Non-inferiority and superiority are defined through the hypothesis \((\lambda_P - \lambda_E)/(\lambda_P - \lambda_R) \le \Delta\) with the alternative hypothesis \((\lambda_P - \lambda_E)/(\lambda_P - \lambda_R) > \Delta\). The parameters \(\lambda_E\), \(\lambda_R\), and \(\lambda_P\) are associated with the distribution of the endpoints and smaller values of \(\lambda_E\), \(\lambda_R\), and \(\lambda_P\) are considered to be desirable. A detailed description of these parameters can be found in the help file of the individual functions. The margin \(\Delta\) is between 0 and 1 for testing non-inferiority and larger than 1 for testing superiority.
A detailed discussion of the hypothesis can be found in Hauschke and Pigeot (2005).
The statistical theory for negative binomial distributed endpoint has been developed by Muetze et al. (2015).
Tobias Muetze tobias.muetze@outlook.com
Hauschke, D. and Pigeot, I. 2005. “Establishing efficacy of a new experimental treatment in the 'gold standard' design.” Biometrical Journal 47, 782--786. Muetze, T. et al. 2015. “Design and analysis of three-arm trials with negative binomially distributed endpoints.” Submitted.