Kaniadakis distribution

In statistics, a Kaniadakis distribution (also known as κ-distribution) is a statistical distribution that emerges from the Kaniadakis statistics.

Uses your system voice; voice and rate in settings.

Snapshot

≈ 5 min read

Names in other languages

No names in other languages are held for this entry yet.

Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.

In statistics, a Kaniadakis distribution (also known as κ-distribution) is a statistical distribution that emerges from the Kaniadakis statistics. There are several families of Kaniadakis distributions related to different constraints used in the maximization of the Kaniadakis entropy, such as the κ-Exponential distribution, κ-Gaussian distribution, Kaniadakis κ-Gamma distribution and κ-Weibull distribution.

The κ-distributions have been applied for modeling a vast phenomenology of experimental statistical distributions in natural or artificial complex systems, such as, in epidemiology, quantum statistics, in astrophysics and cosmology, in geophysics, in economy, in machine learning. The κ-distributions are written as function of the κ-deformed exponential, taking the form : f_i=\exp_{\kappa}(-\beta E_i+\beta \mu) enables the power-law description of complex systems following the consistent κ-generalized statistical theory., where \exp_{\kappa}(x)=(\sqrt{1+ \kappa^2 x^2}+\kappa x)^{1/\kappa} is the Kaniadakis κ-exponential function.

The κ-distribution becomes the common Boltzmann distribution at low energies, while it has a power-law tail at high energies, the feature of high interest of many researchers.

In statistics, a Kaniadakis distribution (also known as κ-distribution) is a statistical distribution that emerges from the Kaniadakis statistics. There are several families of Kaniadakis distributions related to different constraints used in the maximization of the Kaniadakis entropy, such as the κ-Exponential distribution, κ-Gaussian distribution, Kaniadakis κ-Gamma distribution and κ-Weibull distribution.

The κ-distributions have been applied for modeling a vast phenomenology of experimental statistical distributions in natural or artificial complex systems, such as, in epidemiology, quantum statistics, in astrophysics and cosmology, in geophysics, in economy, in machine learning. The κ-distributions are written as function of the κ-deformed exponential, taking the form f_i=\exp_{\kappa}(-\beta E_i+\beta \mu) enables the power-law description of complex systems following the consistent κ-generalized statistical theory., where \exp_{\kappa}(x)=(\sqrt{1+ \kappa^2 x^2}+\kappa x)^{1/\kappa} is the Kaniadakis κ-exponential function.

The κ-distribution becomes the common Boltzmann distribution at low energies, while it has a power-law tail at high energies, the feature of high interest of many researchers. κ-Exponential distribution of Type I when \alpha = \nu = 1 . κ-Erlang distribution when \alpha = 1 and \nu = n = positive integer. κ-Half-Normal distribution, when \alpha = 2 and \nu = 1/2 . Generalized Gamma distribution, when \alpha = 1 ; In the limit \kappa \rightarrow 0 , the κ-Gamma distribution becomes a ... Erlang distribution, when \alpha = 1 and \nu = n = positive integer; Chi-Squared distribution, when \alpha = 1 and \nu = half integer; Nakagami distribution, when \alpha = 2 and \nu > 0 ; Rayleigh distribution, when \alpha = 2 and \nu = 1 ; Chi distribution, when \alpha = 2 and \nu = half integer; Maxwell distribution, when \alpha = 2 and \nu = 3/2 ; Half-Normal distribution, when \alpha = 2 and \nu = 1/2 ; Weibull distribution, when \alpha > 0 and \nu = 1 ; Stretched Exponential distribution, when \alpha > 0 and \nu = 1/\alpha ; | name = κ-Distribution Type IV | type = density | parameters = 0 \leq \kappa \alpha > 0 shape (real) \beta> 0 rate (real) | support = x \in [0, +\infty) | pdf = \frac{\alpha}{\kappa} (2\kappa \beta )^{1/\kappa } \left(1 - \frac{\kappa \beta x^\alpha}{\sqrt{1+\kappa^2\beta^2x^{2\alpha} } } \right) x^{ -1 + \alpha / \kappa} \exp_\kappa(-\beta x^\alpha) | cdf = (2\kappa \beta )^{1/\kappa} x^{\alpha / \kappa} \exp_\kappa(-\beta x^\alpha) |moments= \frac{(2 \kappa \beta)^{-m/\alpha} }{ 1 + \kappa \frac{ m }{ 2\alpha } } \frac{\Gamma\Big(\frac{1}{\kappa} + \frac{m}{\alpha}\Big) \Gamma\Big(1 - \frac{m}{2\alpha}\Big)}{\Gamma\Big(\frac{1}{\kappa} + \frac{m}{2\alpha}\Big)} |pdf_image=FILE:Kaniadakis typeIV Distribution pdf.png|pdf_caption=Plot of the κ-Distribution Type IV for typical κ-values, and \alpha = \beta = 1 .|cdf_image=FILE:Kaniadakis typeIV Distribution cdf.png}} The Kaniadakis distribution of Type IV (or κ-Distribution Type IV) is a three-parameter family of continuous statistical distributions.

The κ-Distribution Type IV distribution has the following probability density function: f_{_{\kappa}}(x) = \frac{\alpha}{\kappa} (2\kappa \beta )^{1/\kappa} \left(1 - \frac{\kappa \beta x^\alpha}{\sqrt{1+\kappa^2\beta^2x^{2\alpha} } } \right) x^{ -1 + \alpha / \kappa} \exp_\kappa(-\beta x^\alpha) valid for x \geq 0 , where 0 \leq |\kappa| is the entropic index associated with the Kaniadakis entropy, \beta > 0 is the scale parameter, and \alpha > 0 is the shape parameter. The cumulative distribution function of κ-Distribution Type IV assumes the form: F_\kappa(x) = (2\kappa \beta )^{1/\kappa} x^{\alpha / \kappa} \exp_\kappa(-\beta x^\alpha) The κ-Distribution Type IV does not admit a classical version, since the probability function and its cumulative reduces to zero in the classical limit \kappa \rightarrow 0 .

Its moment of order m given by \operatorname{E}[X^m] = \frac{(2 \kappa \beta)^{-m/\alpha} }{ 1 + \kappa \frac{ m }{ 2\alpha } } \frac{\Gamma\Big(\frac{1}{\kappa} + \frac{m}{\alpha}\Big) \Gamma\Big(1 - \frac{m}{2\alpha}\Big)}{\Gamma\Big(\frac{1}{\kappa} + \frac{m}{2\alpha}\Big)} The moment of order m of the κ-Distribution Type IV is finite for m . Giorgio Kaniadakis Google Scholar page Kaniadakis Statistics on arXiv.org

Text derived from https://en.wikipedia.org/w/index.php?oldid=1369381176 under CC BY-SA 4.0; modifications have been made.

Sources cited in this revision

10 named source(s) extracted from the cited revision. A source with no author is shown by its publication; nothing is invented.