Generalized Pareto distribution

In statistics, the generalized Pareto distribution (GPD) is a family of continuous probability distributions. It is often used to model the tails of another distribution. It is specified by three parameters: location ${\displaystyle \mu }$, scale ${\displaystyle \sigma }$, and shape ${\displaystyle \xi }$.[1][2] Sometimes it is specified by only scale and shape[3] and sometimes only by its shape parameter. Some references give the shape parameter as ${\displaystyle \kappa =-\xi \,}$.[4]

This article is about a particular family of continuous distributions referred to as the generalized Pareto distribution. For the hierarchy of generalized Pareto distributions, see Pareto distribution.

Generalized Pareto distribution

Probability density function GPD distribution functions for ${\displaystyle \mu =0}$ and different values of ${\displaystyle \sigma }$ and ${\displaystyle \xi }$
Cumulative distribution function
Parameters	${\displaystyle \mu \in (-\infty ,\infty )\,}$ location (real) ${\displaystyle \sigma \in (0,\infty )\,}$ scale (real) ${\displaystyle \xi \in (-\infty ,\infty )\,}$ shape (real)
Support	${\displaystyle x\geqslant \mu \,\;(\xi \geqslant 0)}$ ${\displaystyle \mu \leqslant x\leqslant \mu -\sigma /\xi \,\;(\xi <0)}$
PDF	${\displaystyle {\frac {1}{\sigma }}(1+\xi z)^{-(1/\xi +1)}}$ where ${\displaystyle z={\frac {x-\mu }{\sigma }}}$
CDF	${\displaystyle 1-(1+\xi z)^{-1/\xi }\,}$
Mean	${\displaystyle \mu +{\frac {\sigma }{1-\xi }}\,\;(\xi <1)}$
Median	${\displaystyle \mu +{\frac {\sigma (2^{\xi }-1)}{\xi }}}$
Mode
Variance	${\displaystyle {\frac {\sigma ^{2}}{(1-\xi )^{2}(1-2\xi )}}\,\;(\xi <1/2)}$
Skewness	${\displaystyle {\frac {2(1+\xi ){\sqrt {1-2\xi }}}{(1-3\xi )}}\,\;(\xi <1/3)}$
Ex. kurtosis	${\displaystyle {\frac {3(1-2\xi )(2\xi ^{2}+\xi +3)}{(1-3\xi )(1-4\xi )}}-3\,\;(\xi <1/4)}$
Entropy	${\displaystyle \log(\sigma )+\xi +1}$
MGF	${\displaystyle e^{\theta \mu }\,\sum _{j=0}^{\infty }\left[{\frac {(\theta \sigma )^{j}}{\prod _{k=0}^{j}(1-k\xi )}}\right],\;(k\xi <1)}$
CF	${\displaystyle e^{it\mu }\,\sum _{j=0}^{\infty }\left[{\frac {(it\sigma )^{j}}{\prod _{k=0}^{j}(1-k\xi )}}\right],\;(k\xi <1)}$
Method of Moments	${\displaystyle \xi ={\frac {1}{2}}\left(1-{\frac {(E[X]-\mu )^{2}}{V[X]}}\right)}$ ${\displaystyle \sigma =(E[X]-\mu )(1-\xi )}$

Definition

The standard cumulative distribution function (cdf) of the GPD is defined by[5]

${\displaystyle F_{\xi }(z)={\begin{cases}1-\left(1+\xi z\right)^{-1/\xi }&{\text{for }}\xi \neq 0,\\1-e^{-z}&{\text{for }}\xi =0.\end{cases}}}$

where the support is ${\displaystyle z\geq 0}$ for ${\displaystyle \xi \geq 0}$ and ${\displaystyle 0\leq z\leq -1/\xi }$ for ${\displaystyle \xi <0}$. The corresponding probability density function (pdf) is

${\displaystyle f_{\xi }(z)={\begin{cases}(1+\xi z)^{-{\frac {\xi +1}{\xi }}}&{\text{for }}\xi \neq 0,\\e^{-z}&{\text{for }}\xi =0.\end{cases}}}$

Characterization

The related location-scale family of distributions is obtained by replacing the argument z by ${\displaystyle {\frac {x-\mu }{\sigma }}}$ and adjusting the support accordingly.

The cumulative distribution function of ${\displaystyle X\sim GPD(\mu ,\sigma ,\xi )}$ (${\displaystyle \mu \in \mathbb {R} }$, ${\displaystyle \sigma >0}$, and ${\displaystyle \xi \in \mathbb {R} }$) is

${\displaystyle F_{(\mu ,\sigma ,\xi )}(x)={\begin{cases}1-\left(1+{\frac {\xi (x-\mu )}{\sigma }}\right)^{-1/\xi }&{\text{for }}\xi \neq 0,\\1-\exp \left(-{\frac {x-\mu }{\sigma }}\right)&{\text{for }}\xi =0,\end{cases}}}$

where the support of ${\displaystyle X}$ is ${\displaystyle x\geqslant \mu }$ when ${\displaystyle \xi \geqslant 0\,}$, and ${\displaystyle \mu \leqslant x\leqslant \mu -\sigma /\xi }$ when ${\displaystyle \xi <0}$.

The probability density function (pdf) of ${\displaystyle X\sim GPD(\mu ,\sigma ,\xi )}$ is

${\displaystyle f_{(\mu ,\sigma ,\xi )}(x)={\frac {1}{\sigma }}\left(1+{\frac {\xi (x-\mu )}{\sigma }}\right)^{\left(-{\frac {1}{\xi }}-1\right)}}$,

again, for ${\displaystyle x\geqslant \mu }$ when ${\displaystyle \xi \geqslant 0}$, and ${\displaystyle \mu \leqslant x\leqslant \mu -\sigma /\xi }$ when ${\displaystyle \xi <0}$.

The pdf is a solution of the following differential equation:

${\displaystyle \left\{{\begin{array}{l}f'(x)(-\mu \xi +\sigma +\xi x)+(\xi +1)f(x)=0,\\f(0)={\frac {\left(1-{\frac {\mu \xi }{\sigma }}\right)^{-{\frac {1}{\xi }}-1}}{\sigma }}\end{array}}\right\}}$

Special cases

• If the shape ${\displaystyle \xi }$ and location ${\displaystyle \mu }$ are both zero, the GPD is equivalent to the exponential distribution.
• With shape ${\displaystyle \xi >0}$ and location ${\displaystyle \mu =\sigma /\xi }$, the GPD is equivalent to the Pareto distribution with scale ${\displaystyle x_{m}=\sigma /\xi }$ and shape ${\displaystyle \alpha =1/\xi }$.
• If ${\displaystyle X}$ ${\displaystyle \sim }$ ${\displaystyle GPD}$ ${\displaystyle (}$${\displaystyle \mu =0}$, ${\displaystyle \sigma }$, ${\displaystyle \xi }$ ${\displaystyle )}$, then ${\displaystyle Y=\log(X)\sim exGPD(\sigma ,\xi )}$ . (exGPD stands for the exponentiated generalized Pareto distribution.)
• GPD is similar to the Burr distribution.

Generating generalized Pareto random variables

Generating GPD random variables

If U is uniformly distributed on (0, 1], then

${\displaystyle X=\mu +{\frac {\sigma (U^{-\xi }-1)}{\xi }}\sim GPD(\mu ,\sigma ,\xi \neq 0)}$

and

${\displaystyle X=\mu -\sigma \ln(U)\sim GPD(\mu ,\sigma ,\xi =0).}$

Both formulas are obtained by inversion of the cdf.

In Matlab Statistics Toolbox, you can easily use "gprnd" command to generate generalized Pareto random numbers.

GPD as an Exponential-Gamma Mixture

A GPD random variable can also be expressed as an exponential random variable, with a Gamma distributed rate parameter.

${\displaystyle X|\Lambda \sim Exp(\Lambda )}$

and

${\displaystyle \Lambda \sim Gamma(\alpha ,\beta )}$

then

${\displaystyle X\sim GPD(\xi =1/\alpha ,\ \sigma =\beta /\alpha )}$

Notice however, that since the parameters for the Gamma distribution must be greater than zero, we obtain the additional restrictions that:${\displaystyle \xi }$ must be positive.

Exponentiated generalized Pareto distribution

The exponentiated generalized Pareto distribution (exGPD)

The pdf of the ${\displaystyle exGPD(\sigma ,\xi )}$ (exponentiated generalized Pareto distribution) for different values ${\displaystyle \sigma }$ and ${\displaystyle \xi }$.

If ${\displaystyle X\sim GPD}$ ${\displaystyle (}$${\displaystyle \mu =0}$, ${\displaystyle \sigma }$, ${\displaystyle \xi }$ ${\displaystyle )}$, then ${\displaystyle Y=\log(X)}$ is distributed according to the exponentiated generalized Pareto distribution, denoted by ${\displaystyle Y}$ ${\displaystyle \sim }$ ${\displaystyle exGPD}$ ${\displaystyle (}$${\displaystyle \sigma }$, ${\displaystyle \xi }$ ${\displaystyle )}$.

The probability density function(pdf) of ${\displaystyle Y}$ ${\displaystyle \sim }$ ${\displaystyle exGPD}$ ${\displaystyle (}$${\displaystyle \sigma }$, ${\displaystyle \xi }$ ${\displaystyle )\,\,(\sigma >0)}$ is

${\displaystyle g_{(\sigma ,\xi )}(y)={\begin{cases}{\frac {e^{y}}{\sigma }}{\bigg (}1+{\frac {\xi e^{y}}{\sigma }}{\bigg )}^{-1/\xi -1}\,\,\,\,{\text{for }}\xi \neq 0,\\{\frac {1}{\sigma }}e^{y-e^{y}/\sigma }\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,{\text{for }}\xi =0,\end{cases}}}$

where the support is ${\displaystyle -\infty <y<\infty }$ for ${\displaystyle \xi \geq 0}$, and ${\displaystyle -\infty <y\leq \log(-\sigma /\xi )}$ for ${\displaystyle \xi <0}$.

For all ${\displaystyle \xi }$, the ${\displaystyle \log \sigma }$ becomes the location parameter. See the right panel for the pdf when the shape ${\displaystyle \xi }$ is positive.

The exGPD has finite moments of all orders for all ${\displaystyle \sigma >0}$ and ${\displaystyle -\infty <\xi <\infty }$.

The variance of the ${\displaystyle exGPD(\sigma ,\xi )}$ as a function of ${\displaystyle \xi }$. The red dotted line corresponds to the value of variance (${\displaystyle \psi ^{'}(1)=\pi ^{2}/6}$) evaluated at ${\displaystyle \xi =0}$.

The moment-generating function of ${\displaystyle Y\sim exGPD(\sigma ,\xi )}$ is

${\displaystyle M_{Y}(s)=E[e^{sY}]={\begin{cases}-{\frac {1}{\xi }}{\bigg (}-{\frac {\sigma }{\xi }}{\bigg )}^{s}B(s+1,-1/\xi )\,\,\,\,\,\,\,\,\,\,\,\,{\text{for }}s\in (-1,\infty ),\xi <0,\\{\frac {1}{\xi }}{\bigg (}{\frac {\sigma }{\xi }}{\bigg )}^{s}B(s+1,1/\xi -s)\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,{\text{for }}s\in (-1,1/\xi ),\xi >0,\\\sigma ^{s}\Gamma (1+s)\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,{\text{for }}s\in (-1,\infty ),\xi =0,\end{cases}}}$

where ${\displaystyle B(a,b)}$ and ${\displaystyle \Gamma (a)}$ denote the beta function and gamma function, respectively.

The variance of ${\displaystyle Y}$ ${\displaystyle \sim }$ ${\displaystyle exGPD}$ ${\displaystyle (}$${\displaystyle \sigma }$, ${\displaystyle \xi }$ ${\displaystyle )}$ depends on the shape parameter ${\displaystyle \xi }$ only through the polygamma function of order 1 (also called the trigamma function):

${\displaystyle Var(Y)={\begin{cases}\psi ^{'}(1)-\psi ^{'}(-1/\xi +1)\,\,\,\,\,\,\,\,\,\,\,\,{\text{for }}\xi <0,\\\psi ^{'}(1)+\psi ^{'}(1/\xi )\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,{\text{for }}\xi >0,\\\psi ^{'}(1)\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,\,{\text{for }}\xi =0.\end{cases}}}$

See the right panel for the variance as a function of ${\displaystyle \xi }$. Note that ${\displaystyle \psi ^{'}(1)=\pi ^{2}/6\approx 1.644934}$.

Note that the roles of the scale parameter ${\displaystyle \sigma }$ and the shape parameter ${\displaystyle \xi }$ under ${\displaystyle Y\sim exGPD(\sigma ,\xi )}$ are separably interpretable, which may lead to a robust efficient estimation for the ${\displaystyle \xi }$ than using the ${\displaystyle X\sim GPD(\sigma ,\xi )}$ . The roles of the two parameters are associated each other under ${\displaystyle X\sim GPD(\mu =0,\sigma ,\xi )}$ (at least upto the second central moment); see the formula of variance ${\displaystyle Var(X)}$ wherein both parameters are participated.

The Hill's estimator

Assume that ${\displaystyle X_{1:n}=(X_{1},\cdots ,X_{n})}$ are ${\displaystyle n}$ observations (not need to be i.i.d.) from an unknown heavy-tailed distribution ${\displaystyle F}$ such that its tail distribution is regularly varying with the tail-index ${\displaystyle 1/\xi }$ (hence, the corresponding shape parameter is ${\displaystyle \xi }$). To be specific, the tail distribution is described as

${\displaystyle {\bar {F}}(x)=1-F(x)=L(x)\cdot x^{-1/\xi },\,\,\,\,\,{\text{for some }}\xi >0,\,\,{\text{where }}L{\text{ is a slowly varying function.}}}$

It is of a particular interest in the extreme value theory to estimate the shape parameter ${\displaystyle \xi }$, especially when ${\displaystyle \xi }$ is positive (so called the heavy-tailed distribution).

Let ${\displaystyle F_{u}}$ be their conditional excess distribution function. Pickands–Balkema–de Haan theorem (Pickands, 1975; Balkema and de Haan, 1974) states that for a large class of underlying distribution functions ${\displaystyle F}$, and large ${\displaystyle u}$, ${\displaystyle F_{u}}$ is well approximated by the generalized Pareto distribution (GPD), which motivated Peak Over Threshold (POT) methods to estimate ${\displaystyle \xi }$: the GPD plays the key role in POT approach.

A renowned estimator using the POT methodology is the Hill's estimator. Technical formulation of the Hill's estimator is as follows. For ${\displaystyle 1\leq i\leq n}$, write ${\displaystyle X_{(i)}}$ for the ${\displaystyle i}$-th largest value of ${\displaystyle X_{1},\cdots ,X_{n}}$. Then, with this notation, the Hill's estimator (see page 190 of Reference 5 by Embrechts et al ) based on the ${\displaystyle k}$ upper order statistics is defined as

${\displaystyle {\widehat {\xi }}_{k}^{\text{Hill}}={\widehat {\xi }}_{k}^{\text{Hill}}(X_{1:n})={\frac {1}{k-1}}\sum _{j=1}^{k-1}\log {\bigg (}{\frac {X_{(j)}}{X_{(k)}}}{\bigg )},\,\,\,\,\,\,\,\,{\text{for }}2\leq k\leq n.}$

In practice, the Hill estimator is used as follows. First, calculate the estimator ${\displaystyle {\widehat {\xi }}_{k}^{\text{Hill}}}$ at each integer ${\displaystyle k\in \{2,\cdots ,n\}}$, and then plot the ordered pairs ${\displaystyle \{(k,{\widehat {\xi }}_{k}^{\text{Hill}})\}_{k=2}^{n}}$. Then, select from the set of Hill estimators ${\displaystyle \{{\widehat {\xi }}_{k}^{\text{Hill}}\}_{k=2}^{n}}$ which are roughly constant with respect to ${\displaystyle k}$: these stable values are regarded as reasonable estimates for the shape parameter ${\displaystyle \xi }$. If ${\displaystyle X_{1},\cdots ,X_{n}}$ are i.i.d., then the Hill's estimator is a consistent estimator for the shape parameter ${\displaystyle \xi }$ .

Note that the Hill estimator ${\displaystyle {\widehat {\xi }}_{k}^{\text{Hill}}}$ makes a use of the log-transformation for the observations ${\displaystyle X_{1:n}=(X_{1},\cdots ,X_{n})}$. (The Pickand's estimator ${\displaystyle {\widehat {\xi }}_{k}^{\text{Pickand}}}$ also employed the log-transformation, but in a slightly different way .)

See also

• Burr distribution
• Pareto distribution
• Generalized extreme value distribution
• Exponentiated generalized Pareto distribution
• Pickands–Balkema–de Haan theorem

References

1. Coles, Stuart (2001-12-12). An Introduction to Statistical Modeling of Extreme Values. Springer. p. 75. ISBN 9781852334598.
2. Dargahi-Noubary, G. R. (1989). "On tail estimation: An improved method". Mathematical Geology. 21 (8): 829–842. doi:10.1007/BF00894450.
3. Hosking, J. R. M.; Wallis, J. R. (1987). "Parameter and Quantile Estimation for the Generalized Pareto Distribution". Technometrics. 29 (3): 339–349. doi:10.2307/1269343. JSTOR 1269343.
4. Davison, A. C. (1984-09-30). "Modelling Excesses over High Thresholds, with an Application". In de Oliveira, J. Tiago (ed.). Statistical Extremes and Applications. Kluwer. p. 462. ISBN 9789027718044.
5. Embrechts, Paul; Klüppelberg, Claudia; Mikosch, Thomas (1997-01-01). Modelling extremal events for insurance and finance. p. 162. ISBN 9783540609315.

Further reading

• Pickands, James (1975). "Statistical inference using extreme order statistics". Annals of Statistics. 3 s: 119–131. doi:10.1214/aos/1176343003.
• Balkema, A.; De Haan, Laurens (1974). "Residual life time at great age". Annals of Probability. 2 (5): 792–804. doi:10.1214/aop/1176996548.
• Lee, Seyoon; Kim, J.H.K. (2018). "Exponentiated generalized Pareto distribution:Properties and applications towards extreme value theory". Communications in Statistics - Theory and Methods. 0: 1–25. arXiv:1708.01686. doi:10.1080/03610926.2018.1441418.
• N. L. Johnson; S. Kotz; N. Balakrishnan (1994). Continuous Univariate Distributions Volume 1, second edition. New York: Wiley. ISBN 978-0-471-58495-7.CS1 maint: ref=harv (link) Chapter 20, Section 12: Generalized Pareto Distributions.
• Barry C. Arnold (2011). "Chapter 7: Pareto and Generalized Pareto Distributions". In Duangkamon Chotikapanich (ed.). Modeling Distributions and Lorenz Curves. New York: Springer. ISBN 9780387727967.CS1 maint: ref=harv (link)
• Arnold, B. C.; Laguna, L. (1977). On generalized Pareto distributions with applications to income data. Ames, Iowa: Iowa State University, Department of Economics.CS1 maint: ref=harv (link)

External links

• Mathworks: Generalized Pareto distribution