An Approximate Iterative Algorithm for Modeling of Non-Gaussian Vectors with Given Marginal Distributions and Covariance Matrix

IF 0.4 Q4 MATHEMATICS, APPLIED

Numerical Analysis and Applications Pub Date : 2023-12-07 DOI:10.1134/s1995423923040018

M. S. Akenteva, N. A. Kargapolova, V. A. Ogorodnikov

引用次数: 0

Abstract

A new iterative method for modeling of non-Gaussian random vectors with given marginal distributions and a covariance matrix is proposed in this paper. The algorithm is compared with another iterative algorithm for modeling of non-Gaussian vectors, based on reordering of a sample of independent random variables with given marginal distributions. Our numerical studies show that both algorithms are equivalent in terms of the accuracy of reproduction of a given covariance matrix, but the offered algorithm turns out to be more efficient in terms of memory usage and, in many cases, is faster than the other one.

查看原文本刊更多论文

用给定边际分布和协方差矩阵建立非高斯向量模型的近似迭代算法

摘要本文提出了一种新的迭代法，用于给定边际分布和协方差矩阵的非高斯随机向量建模。该算法与另一种非高斯向量建模迭代算法进行了比较，后者是基于对给定边际分布的独立随机变量样本进行重新排序。我们的数值研究表明，就给定协方差矩阵的再现精度而言，这两种算法是等效的，但所提供的算法在内存使用方面更有效，而且在许多情况下比另一种算法更快。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Numerical Analysis and Applications MATHEMATICS, APPLIED-

CiteScore

1.00

自引率

0.00%

发文量

期刊介绍： Numerical Analysis and Applications is the translation of Russian periodical Sibirskii Zhurnal Vychislitel’noi Matematiki (Siberian Journal of Numerical Mathematics) published by the Siberian Branch of the Russian Academy of Sciences Publishing House since 1998. The aim of this journal is to demonstrate, in concentrated form, to the Russian and International Mathematical Community the latest and most important investigations of Siberian numerical mathematicians in various scientific and engineering fields. The journal deals with the following topics: Theory and practice of computational methods, mathematical physics, and other applied fields; Mathematical models of elasticity theory, hydrodynamics, gas dynamics, and geophysics; Parallelizing of algorithms; Models and methods of bioinformatics.