Permutation Tests for Matched Pairs with Adjustments for Covariates
针对观察性研究中匹配后仍存在协变量差异的问题，提出一种通用的置换检验方法，可调整配对内的协变量差异，适用于连续和二元响应。
SUMMARY In observational studies, treated and control subjects are often matched on the basis of observed covariates to permit comparisons of subjects who appeared similar before treatment. In many studies, however, it is not possible to find an exact match for every treated subject, so that within matched pairs treated and control subjects may still differ with respect to some observed covariates. This paper discusses a simple general method for obtaining permutation inferences that adjust for such observed differences within pairs. The method generalizes both the Wilcoxon signed rank test for continuous responses and the McNemar-Cox test for binary responses, as well as many other permutation tests for matched paris.