Distance‐based regression model has become a powerful approach to identifying phenotypic associations in many fields. It is found to be particularly useful for high‐dimensional biological and genetic data with proper distance or similarity measures being available. The pseudo F statistic used in this model accumulates information and is effective when the signals, that is the variations represented by the eigenvalues of the similarity matrix, scatter evenly along the eigenvectors of the similarity matrix. However, it might lose power for the uneven signals. To deal with this issue, we propose a group analysis on the variations of signals along the eigenvalues of the similarity matrix and take the maximum among them. The new procedure can automatically choose an optimal grouping point on some given thresholds and thus can improve the power evidence. Extensive computer simulations and applications to a prostate cancer data and an aging human brain data illustrate the effectiveness of the proposed method.

中文翻译：

---

距离矩阵的组分析。

基于距离的回归模型已成为在许多领域识别表型关联的有效方法。发现它对于具有适当距离或相似性度量的高维生物学和遗传数据特别有用。伪F该模型中使用的统计信息会累积信息，并且当信号（即由相似度矩阵特征值表示的变化）沿相似度矩阵的特征向量均匀分散时有效。但是，由于信号不均匀，可能会断电。为了解决这个问题，我们提出了对信号沿着相似度矩阵特征值的变化进行分组分析的方法，并在其中取最大值。新过程可以在某些给定阈值上自动选择最佳分组点，从而可以改善功效证据。广泛的计算机模拟以及对前列腺癌数据和人脑老化数据的应用说明了所提出方法的有效性。