We propose a new method for generating random correlation matrices that makes it simple to control both location and dispersion. The method is based on a vector parameterization, gamma = g(C), which maps any distribution on R^d, d = n(n-1)/2 to a distribution on the space of non-singular nxn correlation matrices. Correlation matrices with certain properties, such as being well-conditioned, having block structures, and having strictly positive elements, are simple to generate. We compare the new method with existing methods.
翻译:我们提出一种新的随机相关矩阵生成方法,使控制位置和分散都简单。该方法基于矢量参数化,伽马=g(C),该方法将R ⁇ d、d=n(n-1)/2上的任何分布映射到非星系 nxn 相关矩阵空间的分布中。与某些属性的关联矩阵,如条件良好、有块状结构、具有严格肯定元素等,很容易生成。我们将新方法与现有方法进行比较。