A joint mix is a random vector with a constant component-wise sum. It is known to represent the minimizing dependence structure of some common objectives, and it is usually regarded as a concept of extremal negative dependence. In this paper, we explore the connection between the joint mix structure and one of the most popular notions of negative dependence in statistics, called negative orthant dependence (NOD). We show that a joint mix does not always have NOD, but some natural classes of joint mixes have. In particular, the Gaussian class is characterized as the only elliptical class which supports NOD joint mixes of arbitrary dimension. For Gaussian margins, we also derive a necessary and sufficient condition for the existence of an NOD joint mix. Finally, for identical marginal distributions, we show that an NOD Gaussian joint mix solves a multi-marginal optimal transport problem under uncertainty on the number of components. Analysis of this optimal transport problem with heterogeneous marginals reveals a trade-off between NOD and the joint mix structure.
翻译:联合混合是一种随机的矢量, 具有恒定的成分和总和。 已知它代表着某些共同目标的最小依赖性结构, 通常被视为极端负依赖性的概念。 在本文中, 我们探讨了联合混合结构与统计中最流行的负依赖性概念之一( 称为负或绝对依赖性( NOD) 之间的联系。 我们显示, 联合混合并不总是有NOD, 但有些天然的混合型混合型。 特别是, 高西亚级被定性为唯一支持NOD任意性联合组合的椭圆类。 对于高斯边缘, 我们还为NOD联合组合的存在创造了必要和充分的条件。 最后, 对于相同的边际分布, 我们显示, NOD Gausian 联合混合型混合型在组件数量不确定的情况下解决了多边际最佳运输问题。 分析这一与多元边缘的优化运输问题揭示了NOD与联合混合型结构之间的利差。