Critical Analysis of Beta Random Variable Generation Methods

Author:

Almaraz Luengo Elena1ORCID,Gragera Carlos2

Affiliation:

1. Department of Statistics and Operational Research, Faculty of Mathematical Science, Complutense University of Madrid, 28040 Madrid, Spain

2. Faculty of Mathematical Science, Complutense University of Madrid, 28040 Madrid, Spain

Abstract

The fast generation of values of the beta random variable is a subject of great interest and multiple applications, ranging from purely mathematical and statistical ones to applications in management and production, among others. There are several methods for generating these values, with one of the essential points for their design being the selection of random seeds. Two interesting aspects converge here: the use of sequences as inputs (and the need for them to verify properties such as randomness and uniformity, which are verified through statistical test suites) and the design of the algorithm for the generation of the variable. In this paper, we analyse, in detail, the algorithms that have been developed in the literature, both from a mathematical/statistical and computational point of view. We also provide empirical development using R software, which is currently in high demand and is one of the main novelties with respect to previous comparisons carried out in FORTRAN. We establish which algorithms are more efficient and in which contexts, depending on the different values of the parameters, allowing the user to determine the best method given the experimental conditions.

Publisher

MDPI AG

Subject

General Mathematics,Engineering (miscellaneous),Computer Science (miscellaneous)

Reference64 articles.

1. Gaussian Random Number Generators;Thomas;ACM Computing Surv.,2007

2. Gaussian Random Number Generation: A Survey on Hardware Architectures;Malik;ACM Comput. Surv.,2016

3. Maatouk, H., and Bay, X. (2016). Mathematics in Monte Carlo and Quasi-Monte Carlo Methods, Springer.

4. Morán-Vásquez, R., Zarrazola, E., and Nagar, D.K. (2023). Some Theoretical and Computational Aspects of the Truncated Multivariate Skew-Normal/Independent Distributions. Mathematics, 11.

5. Gamma Pseudo Random Number Generators;ACM Comput. Surv.,2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3