各位老师大家好，想请教一个问题，我最近在看文献的时候发现，文献在可重复性部分会将原本的数据随机分成2个亚组，然后计算亚组数据集之间的相关性。然后我想问一下，两个数据集之间的矩阵是怎么做相关的，是直接对两个亚组的矩阵求相关系数吗？
我感觉是的。你可以把相关部分的文字描述贴一下或者贴一下文献名字，这样才能更清楚。
文献：Altered functional–structural coupling of large-scale brain networks in idiopathic generalized epilepsy
Reproducibility analysis
文献相关描述：
To test the reproducibility of our results, we carried out a split-half analysis (He et al., 2009; Shu et al., 2011). Specifically, we divided the healthy controls group into two subgroups, matched for age and gender (HC1: 13 participants, four females, age: 22.54 ± 2.14 years; HC2: 13 participants, five females, age: 22.69 ± 2.06 years). Similarly, we divided the GTCS group into two matched subgroups (IGE-GTCS1: 13 participants, five females, age: 24.08 ± 7.03 years; IGE-GTCS2: 13 participants, four females, age: 24.15 ± 6.96 years) (all P > 0.43). For each subgroup, both functional and structural connectivity networks were constructed and analysed analogously to the aforementioned whole-group analysis. To determine whether there was a consistent topological organization in the population (He et al., 2009), we computed Pearson’s correlation coefficients for the correlation patterns of the both functional and structural connectivity networks between HC1 and HC2 subgroups and between IGE-GTCS1 and IGE-GTCS2 subgroups. We also compared the topological parameters (forumla and forumla) between each pair of subgroups using permutation testing.
我看了一下原文，应该就是将分半数据集里产生的两个矩阵直接算相关。功能连接矩阵算一次，结构连接矩阵也算一次。这个连接矩阵就是所谓topological organization。
谢谢老师