Chan Kwun Chuen Gary
Departments of Biostatistics and Health Services, University of Washington, Seattle WA 98195.
Stat Methodol. 2014 Jan 1;16. doi: 10.1016/j.stamet.2013.07.003.
We show that assumptions that are sufficient for estimating an average treatment effect in randomized trials with non-compliance restrict the subgroup means for always takers, compliers, defiers and never takers to a two dimensional linear subspace of a four dimensional space. Implications and specials cases are examplified.
我们表明，在存在不依从性的随机试验中，对于估计平均治疗效果而言足够的假设，将始终接受治疗者、依从者、违抗者和从不接受治疗者的亚组均值限制在四维空间的一个二维线性子空间中。文中举例说明了其影响和特殊情况。
