摘要翻译:
了解变量的统计分布是资源管理中的一个重要问题。幂律型分布在许多实际系统中都可以观察到。然而,幂律分布具有无穷大的方差,因此不能作为标准分布。通常,该领域的专业人员使用参数可变的正态分布或其他近似分布,如Gumbel、Wakeby或Pareto,其有效性有限。Tsallis在非扩展热力学框架下,考虑长程相互作用或长记忆,提出了幂律的微观理论。在本工作中,我们考虑了长程相互作用或记忆的软化,给出了一个具有有限方差的广义分布,可以作为所有具有幂律行为的真实复杂系统的标准分布。我们将这种分布应用于金融系统、降雨和一些地球物理和社会系统。我们发现,在所有情况下,概率密度函数(pdf)和累积概率在整个范围内都有很好的一致性。这种分布表明了实际系统中尺寸限制的普遍性。
---
英文标题:
《The exponentially truncated q-distribution: A generalized distribution
for real complex systems》
---
作者:
Hari M. Gupta, Jose R. Campanha
---
最新提交年份:
2008
---
分类信息:
一级分类:Physics 物理学
二级分类:Statistical Mechanics 统计力学
分类描述:Phase transitions, thermodynamics, field theory, non-equilibrium phenomena, renormalization group and scaling, integrable models, turbulence
相变,热力学,场论,非平衡现象,重整化群和标度,可积模型,湍流
--
一级分类:Quantitative Finance 数量金融学
二级分类:Statistical Finance 统计金融
分类描述:Statistical, econometric and econophysics analyses with applications to financial markets and economic data
统计、计量经济学和经济物理学分析及其在金融市场和经济数据中的应用
--
---
英文摘要:
To know the statistical distribution of a variable is an important problem in management of resources. Distributions of the power law type are observed in many real systems. However power law distributions have an infinite variance and thus can not be used as a standard distribution. Normally professionals in the area use normal distribution with variable parameters or some other approximate distribution like Gumbel, Wakeby, or Pareto, which has limited validity. Tsallis presented a microscopic theory of power law in the framework of non-extensive thermodynamics considering long-range interactions or long memory. In the present work, we consider softing of long-range interactions or memory and presented a generalized distribution which have finite variance and can be used as a standard distribution for all real complex systems with power law behaviour. We applied this distribution for a financial system, rain precipitation and some geophysical and social systems. We found a good agreement for entire range in all cases for the probability density function (pdf) as well as the accumulated probability. This distribution shows universal nature of the size limiting in real systems.
---
PDF链接:
https://arxiv.org/pdf/0807.0563