Tian Hong, Qiao Wenqian, Natarajan Jaya
Johnson & Johnson Pharmaceutical Research & Development, Raritan, New Jersey, USA.
J Biopharm Stat. 2010 May;20(3):632-40. doi: 10.1080/10543400903582034.
Currently, the intersection-union test (IUT) is the standard method of analysis of the data from a thorough QT (TQT) study. In this current work, we compared the methods proposed in three recent publications (Boos et al., 2007; Cheng et al., 2008; Eaton et al., 2006) to IUT using a simulation study. The methods proposed by Cheng and Eaton did not produce a considerable improvement over IUT in the power and size of the test. The power of the Boos et al. method was a substantial improvement over IUT, but the size of the test was found to be greater than 5%.
目前，交并检验（IUT）是全面QT（TQT）研究数据的标准分析方法。在当前这项工作中，我们通过模拟研究，将最近三篇论文（Boos等人，2007年；Cheng等人，2008年；Eaton等人，2006年）中提出的方法与交并检验进行了比较。Cheng和Eaton提出的方法在检验效能和检验水准方面相比交并检验并没有显著改进。Boos等人提出的方法在检验效能上相比交并检验有显著提高，但发现其检验水准大于5%。
