Institute of Statistics, National Central University, Jhongli 320, Taiwan.
Stat Methods Med Res. 2018 Oct;27(10):3077-3091. doi: 10.1177/0962280217691558. Epub 2017 Mar 3.
Pairing serves as a way of lessening heterogeneity but pays the price of introducing more parameters to the model. This complicates the probability structure and makes inference more intricate. We employ the simpler structure of the parallel design to develop a robust score statistic for testing the equality of two multinomial distributions in paired designs. This test incorporates the within-pair correlation in a data-driven manner without a full model specification. In the paired binary data scenario, the robust score statistic turns out to be the McNemar's test. We provide simulations and real data analysis to demonstrate the advantage of the robust procedure.
配对可以作为减少异质性的一种方式，但代价是向模型中引入更多参数。这会使概率结构变得复杂，使推断更加复杂。我们采用平行设计的更简单结构，为配对设计中两个多项分布的相等性检验开发了一个稳健的得分统计量。该检验以数据驱动的方式纳入了个体间相关性，而无需完整的模型指定。在配对二项数据情况下，稳健得分统计量实际上是 McNemar 检验。我们提供了模拟和真实数据分析，以展示稳健程序的优势。
