In this paper, we consider admixture models which are two-component mixture distributions having one known component. This is the case when a gold standard reference component is well known, and when a population contains such a component plus another one with different features. When two populations are drawn from such models, we propose a penalized ${\chi }^2$-type testing procedure allowing a pairwise comparison of the unknown components, i.e. to test the equality of their residual features densities, under a symmetry condition. A numerical study is carried out from a large range of simulation setups to illustrate the asymptotic properties of our test. Moreover the testing procedure is applied on a real-world case: galaxy velocities datasets, where stars heliocentric velocities mixed with the Milky Way are compared.

在本文中，我们考虑混合模型，它是具有一个已知成分的双成分混合分布。当黄金标准参考成分众所周知，并且群体包含这样的成分以及具有不同特征的另一个成分时，就会出现这种情况。当从这样的模型中抽取两个群体时，我们提出了一个惩罚性的${\chi }^2$- 类型测试程序允许对未知组件进行成对比较，即在对称条件下测试其剩余特征密度的相等性。数值研究是从大范围的模拟设置中进行的，以说明我们测试的渐近特性。此外，该测试程序应用于真实世界的案例：星系速度数据集，其中比较了恒星与银河系混合的日心速度。