Scholarlink

<p>We address two important statistical problems: that of estimating mixtures of multivariate normal distributions and mixtures of <i>t</i>-distributions based on univariate projections, and that of quantifying a discrepancy between mixture distributions induced by two model-based clusterings. In the second problem, rather than introducing a direct metric on partitions, we propose a model-based distributional discrepancy between the fitted mixture distributions associated with two clusterings. The results are based on an earlier work of the authors, where it was shown that mixtures of multivariate Gaussian or <i>t</i>-distributions can be distinguished by projecting them onto a certain predetermined finite set of lines, the number of lines depending only on the total number of distributions involved and on the ambient dimension. We also compare our proposal with robust versions of the expectation-maximization method EM. In each case, we present algorithms for effecting the task, and compare them with existing methods by carrying out some simulations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Two statistical problems for multivariate mixture distributions

  • 期刊论文

  • 发表日期：

    2026年6月23日

查看全文
  • Ricardo Fraiman,
  • Leonardo Moreno,
  • Thomas Ransford

摘要

We address two important statistical problems: that of estimating mixtures of multivariate normal distributions and mixtures of t-distributions based on univariate projections, and that of quantifying a discrepancy between mixture distributions induced by two model-based clusterings. In the second problem, rather than introducing a direct metric on partitions, we propose a model-based distributional discrepancy between the fitted mixture distributions associated with two clusterings. The results are based on an earlier work of the authors, where it was shown that mixtures of multivariate Gaussian or t-distributions can be distinguished by projecting them onto a certain predetermined finite set of lines, the number of lines depending only on the total number of distributions involved and on the ambient dimension. We also compare our proposal with robust versions of the expectation-maximization method EM. In each case, we present algorithms for effecting the task, and compare them with existing methods by carrying out some simulations.