Tests for paired count outcomes
Tests for paired count outcomes
复制标题
DOI：
10.1136/gpsych-2018-100004
复制
发表时间：
2018-08-01
影响因子：
11.9
通讯作者：
Tu, Xin M.
中科院分区：
文献类型：
--
作者：
Proudfoot, James A.;Lin, Tuo;Tu, Xin M.
对于中等到较大的样本量，除模型指定错误外，所有测试产生的值都接近标称值。一般来说，带符号秩检验的有效性最低。在计数结果的当前上下文中，与基于完整数据（如GEE）进行对比的测试相比，带符号秩的测试显示出较差的能力。计数结果的参数模型，如具有泊松边际计数结果的GLMM，对偏离假设参数模型非常敏感。对于所有的渐近检验，即有符号秩检验、GLMM和GEE，特别是对于小样本量，都存在一些小偏差。重新采样方法，如置换，可以帮助缓解这种情况。
For moderate to large sample sizes, all tests yielded pvalues close to the nominal, except when models were misspecified. The signed-rank test generally had the lowest power. Within the current context of count outcomes, the signed-rank test shows subpar power when compared with tests that are contrasted based on full data, such as the GEE. Parametric models for count outcomes such as the GLMM with a Poisson for marginal count outcomes are quite sensitive to departures from assumed parametric models. There is some small bias for all the asymptotic tests, that is, the signed-ranktest, GLMM and GEE, especially for small sample sizes. Resampling methods such as permutation can help alleviate this.