Additional file 10 of A Bayesian non-inferiority approach using experts’ margin elicitation – application to the monitoring of safety events

Example of the code to simulate the results for one event (neonatal death): In the part A, it fit margins from experts’ elicitation, using a fictive data set of experts’ answers (E1). In the part B, it simulate the trials and compute the differences of the posterior samplers for M pairs, for one scenario, using one informative prior. In the part C, it calculate the posterior probability that the difference of rate of events is higher than the acceptable difference according to experts, and compute the decision using a threshold of 0.50. (R 26 kb)

针对单一事件（新生儿死亡）的结果模拟代码示例：在模块A中，其采用专家作答虚构数据集（E1），拟合由专家征询（expert elicitation）得到的边际值。在模块B中，其针对单一应用场景，采用单一信息先验（informative prior），对M组配对样本模拟试验过程，并计算其后验采样器（posterior samplers）的差值。在模块C中，其计算事件发生率差值高于专家设定的可接受差值的后验概率，并以0.50作为阈值完成决策判定。（R 26 KB）