In this paper, we deal with the problem of testing the equality of k probability distributions. We introduce a generalization of the maximum mean discrepancy that permits to characterize the null hypothesis. Then we propose its estimator as a test statistic and derive its asymptotic distribution under the null hypothesis. Simulations show that the introduced procedure outperforms a classical one.

中文翻译：

---

基于广义最大均值差异的函数数据 k 样本检验

在本文中，我们处理检验k个概率分布是否相等的问题。我们引入了允许表征零假设的最大平均差异的概括。然后我们提出它的估计量作为检验统计量，并在原假设下推导出它的渐近分布。模拟表明，引入的程序优于经典程序。