Gompertz distribution

{{Short description|Continuous probability distribution, named after Benjamin Gompertz}}

{{more footnotes|date=December 2011}}

{{Probability distribution

| name = Gompertz distribution

| type = density

| pdf_image =325px

| cdf_image =325px

| parameters =shape \eta>0\,\!, scale b > 0\,\!

| support =x \in [0, \infty)\!

| pdf =b\eta \exp\left(\eta + bx -\eta e^{bx} \right)

| cdf =1-\exp\left(-\eta\left(e^{bx}-1 \right)\right)

| quantile =\frac{1}{b}\ln\left(1-\frac{1}{\eta}\ln(1-u)\right)|

| mean =(1/b)e^{\eta}\text{Ei}\left(-\eta\right)
\text {where Ei}\left(z\right)=\int\limits_{-z}^{\infin}\left(e^{-v}/v\right)dv

| median =\left(1/b\right)\ln\left[\left(1/\eta\right)\ln\left(1/2\right)+1\right]

| mode = =\left(1/b\right)\ln \left(1/\eta\right)\
\text {with }0 <\text {F}\left(x^*\right)<1-e^{-1} = 0.632121, 0<\eta<1
=0, \quad \eta \ge 1

| variance =\left(1/b\right)^2 e^{\eta}\{-2\eta { \ }_3\text {F}_3 \left(1,1,1;2,2,2;\eta\right)+\gamma^2

+\left(\pi^2/6\right)+2\gamma\ln\left(\eta\right)+[\ln\left(\eta\right)]^2-e^{\eta}[\text{Ei}\left(-\eta \right)]^2\}
\begin{align}\text{ where } &\gamma \text{ is the Euler constant: }\,\!\\ &\gamma=-\psi\left(1\right)=\text{0.577215... }\end{align}\begin{align}\text { and } { }_3\text {F}_3&\left(1,1,1;2,2,2;-z\right)=\\&\sum_{k=0}^\infty\left[1/\left(k+1\right)^3\right]\left(-1\right)^k\left(z^k/k!\right)\end{align}

| skewness =

| kurtosis =

| entropy =

| mgf =\text{E}\left(e^{-t x}\right)=\eta e^{\eta}\text{E}_{t/b}\left(\eta\right)
\text{with E}_{t/b}\left(\eta\right)=\int_1^\infin e^{-\eta v} v^{-t/b}dv,\ t>0

| char =

}}

In probability and statistics, the Gompertz distribution is a continuous probability distribution, named after Benjamin Gompertz. The Gompertz distribution is often applied to describe the distribution of adult lifespans by demographers and actuaries. Related fields of science such as biology and gerontology also considered the Gompertz distribution for the analysis of survival. More recently, computer scientists have also started to model the failure rates of computer code by the Gompertz distribution. In Marketing Science, it has been used as an individual-level simulation for customer lifetime value modeling. In network theory, particularly the Erdős–Rényi model, the walk length of a random self-avoiding walk (SAW) is distributed according to the Gompertz distribution.Tishby, Biham, Katzav (2016), The distribution of path lengths of self avoiding walks on Erdős-Rényi networks, {{arXiv|1603.06613}}.

Specification

=Probability density function=

The probability density function of the Gompertz distribution is:

:f\left(x;\eta, b\right)=b\eta \exp\left(\eta + b x -\eta e^{bx} \right)\text{for }x \geq 0, \,

where b > 0\,\! is the scale parameter and \eta > 0\,\! is the shape parameter of the Gompertz distribution. In the actuarial and biological sciences and in demography, the Gompertz distribution is parametrized slightly differently (Gompertz–Makeham law of mortality).

=Cumulative distribution function=

The cumulative distribution function of the Gompertz distribution is:

:F\left(x;\eta, b\right)= 1-\exp\left(-\eta\left(e^{bx}-1 \right)\right) ,

where \eta, b>0, and x \geq 0 \, .

=Moment generating function=

The moment generating function is:

:\text{E}\left(e^{-t X}\right)=\eta e^{\eta}\text{E}_{t/b}\left(\eta\right)

where

:\text{E}_{t/b}\left(\eta\right)=\int_1^\infin e^{-\eta v} v^{-t/b}dv,\ t>0.

Properties

The Gompertz distribution is a flexible distribution that can be skewed to the right and to the left. Its hazard function h(x)=\eta b e^{bx} is a convex function of F\left(x;\eta, b\right). The model can be fitted into the innovation-imitation paradigm with

p = \eta b as the coefficient of innovation and b as the coefficient of imitation. When t becomes large, z(t) approaches \infty . The model can also belong to the propensity-to-adopt paradigm with

\eta as the propensity to adopt and b as the overall appeal of the new offering.

=Shapes=

The Gompertz density function can take on different shapes depending on the values of the shape parameter \eta\,\!:

  • When \eta \geq 1,\, the probability density function has its mode at 0.
  • When 0 < \eta < 1,\, the probability density function has its mode at

::x^*=\left(1/b\right)\ln \left(1/\eta\right)\text {with }0 < F\left(x^*\right)<1-e^{-1} = 0.632121

=Kullback-Leibler divergence=

If f_1 and f_2 are the probability density functions of two Gompertz distributions, then their Kullback-Leibler divergence is given by

:

\begin{align}

D_{KL} (f_1 \parallel f_2)

& = \int_{0}^{\infty} f_1(x; b_1, \eta_1) \, \ln \frac{f_1(x; b_1, \eta_1)}{f_2(x; b_2, \eta_2)} dx \\

& = \ln \frac{e^{\eta_1} \, b_1 \, \eta_1}{e^{\eta_2} \, b_2 \, \eta_2}

+ e^{\eta_1} \left[ \left(\frac{b_2}{b_1} - 1 \right) \, \operatorname{Ei}(- \eta_1)

+ \frac{\eta_2}{\eta_1^{\frac{b_2}{b_1}}} \, \Gamma \left(\frac{b_2}{b_1}+1, \eta_1 \right) \right]

- (\eta_1 + 1)

\end{align}

where \operatorname{Ei}(\cdot) denotes the exponential integral and \Gamma(\cdot,\cdot) is the upper incomplete gamma function.Bauckhage, C. (2014), Characterizations and Kullback-Leibler Divergence of Gompertz Distributions, {{arXiv|1402.3193}}.

Related distributions

  • If X is defined to be the result of sampling from a Gumbel distribution until a negative value Y is produced, and setting X=−Y, then X has a Gompertz distribution.
  • The gamma distribution is a natural conjugate prior to a Gompertz likelihood with known scale parameter b \,\!.
  • When \eta\,\! varies according to a gamma distribution with shape parameter \alpha\,\! and scale parameter \beta\,\! (mean = \alpha/\beta\,\!), the distribution of x is Gamma/Gompertz.

File:Gompertz distribution.png

  • If Y \sim \mathrm{Gompertz}, then X = \exp(Y) \sim \mathrm{Weibull}^{-1}, and hence \exp(-Y) \sim \mathrm{Weibull}.{{cite book|last1=Kleiber|first1=Christian|last2=Kotz|first2=Samuel|date=2003|title=Statistical Size Distributions in Economics and Actuarial Sciences|url=https://onlinelibrary.wiley.com/doi/book/10.1002/0471457175|publisher=Wiley|page=179|isbn=9780471150640|doi=10.1002/0471457175}}

Applications

See also

Notes

{{Reflist|refs=

{{cite journal

| last=Bemmaor | first=Albert C. |author2=Glady, Nicolas

| title=Modeling Purchasing Behavior With Sudden 'Death': A Flexible Customer Lifetime Model

| volume = 58 | issue=5 | pages = 1012–1021

| journal=Management Science | year=2012 | doi=10.1287/mnsc.1110.1461}}

{{cite journal

|last=Vaupel | first=James W.

|title=How change in age-specific mortality affects life expectancy

|volume=40 | issue=1 | pages=147–157

|journal=Population Studies

|year=1986 | doi=10.1080/0032472031000141896| pmid=11611920

| url=http://pure.iiasa.ac.at/id/eprint/2683/1/WP-85-017.pdf

}}

{{cite book

|last=Preston | first=Samuel H. |author2=Heuveline, Patrick |author3=Guillot, Michel

|title=Demography:measuring and modeling population processes

|publisher=Blackwell | location=Oxford

|year=2001}}

{{cite book

|last=Benjamin | first=Bernard |author2=Haycocks, H.W. |author3=Pollard, J.

|title=The Analysis of Mortality and Other Actuarial Statistics

|publisher=Heinemann | location=London

|year=1980}}

{{cite journal

|last=Willemse | first=W. J. |author2=Koppelaar, H.

|title=Knowledge elicitation of Gompertz' law of mortality

|journal=Scandinavian Actuarial Journal | volume=2000 |issue=2 | pages=168–179

|year=2000| doi=10.1080/034612300750066845 | s2cid=122719776 }}

{{cite journal

|last=Brown | first=K. |author2=Forbes, W.

|title=A mathematical model of aging processes

|journal=Journal of Gerontology |volume=29 | issue=1 | pages=46–51

|year=1974 | doi=10.1093/geronj/29.1.46| pmid=4809664 }}

{{cite journal

|last=Economos | first=A.

|title=Rate of aging, rate of dying and the mechanism of mortality

|journal=Archives of Gerontology and Geriatrics

|volume=1 | issue=1 | pages=46–51

|year=1982| doi=10.1016/0167-4943(82)90003-6

| pmid=6821142

}}

{{cite journal

|last=Ohishi |first=K. |author2=Okamura, H. |author3=Dohi, T.

|title=Gompertz software reliability model: estimation algorithm and empirical validation

|journal=Journal of Systems and Software

|volume=82 | issue=3 | pages=535–543

|year=2009 |doi=10.1016/j.jss.2008.11.840|url=http://ir.lib.hiroshima-u.ac.jp/00027703 }}

}}

References

  • {{cite web|last1=Bemmaor|first1=Albert C.|last2=Glady|first2=Nicolas|year=2011|title=Implementing the Gamma/Gompertz/NBD Model in MATLAB|url=http://dl.dropbox.com/u/7097708/gg_nbd_MATLAB.pdf|publisher=ESSEC Business School|location=Cergy-Pontoise}}{{Dead link|date=December 2019 |bot=InternetArchiveBot |fix-attempted=yes }}
  • {{Cite journal | last1=Gompertz | first=B. | author-link = Benjamin Gompertz | year= 1825 |pages=513–583| title=On the Nature of the Function Expressive of the Law of Human Mortality, and on a New Mode of Determining the Value of Life Contingencies | journal =Philosophical Transactions of the Royal Society of London|

volume = 115 |jstor=107756 | doi=10.1098/rstl.1825.0026| s2cid=145157003 | url=https://zenodo.org/record/1432356 | doi-access=free }}

  • {{Cite book

| last1=Johnson | first1=Norman L. | last2=Kotz | first2=Samuel

| last3=Balakrishnan | first3=N. | year= 1995

| title=Continuous Univariate Distributions | volume=2

| edition=2nd | publisher=John Wiley & Sons | location=New York

| isbn=0-471-58494-0 | pages=25–26}}

  • {{cite journal|last=Sheikh|first=A. K.|author2=Boah, J. K. |author3=Younas, M. |title=Truncated Extreme Value Model for Pipeline Reliability|journal=Reliability Engineering and System Safety|year=1989|volume = 25|issue=1|pages=1–14 |doi=10.1016/0951-8320(89)90020-3}}

{{ProbDistributions|continuous-semi-infinite}}

Category:Continuous distributions

Category:Survival analysis

Category:Actuarial science