Erlang distribution

Erlang
Probability density function
Cumulative distribution function
Parameters	$\scriptstyle k \;\in\; \mathbb{N}$ shape $\scriptstyle \lambda \;>\; 0$ , rate (real) alt.: $\scriptstyle \mu \;=\; \frac{1}{\lambda} > 0\,$ scale (real)
Support	$\scriptstyle x \;\in\; [0,\, \infty)\!$
PDF	$\scriptstyle \frac{\lambda^k x^{k-1} e^{-\lambda x}}{(k-1)!\,}$
CDF	$\scriptstyle \frac{\gamma(k,\, \lambda x)}{(k \,-\, 1)!} \;=\; 1 \,-\, \sum_{n=0}^{k-1}\frac{1}{n!}e^{-\lambda x}(\lambda x)^{n}$
Mean	$\scriptstyle \frac{k}{\lambda}\,$
Median	No simple closed form
Mode	$\scriptstyle \frac{1}{\lambda}(k \,-\, 1)\,$ for $\scriptstyle k \;\geq\; 1\,$
Variance	$\scriptstyle \frac{k}{\lambda^2}\,$
Skewness	$\scriptstyle \frac{2}{\sqrt{k}}$
Ex. kurtosis	$\scriptstyle \frac{6}{k}$
Entropy	$\scriptstyle (1 \,-\, k)\psi(k) \,+\, \ln\left[\frac{\Gamma(k)}{\lambda}\right] \,+\, k$
MGF	$\scriptstyle \left(1 \,-\, \frac{t}{\lambda}\right)^{-k}\,$ for $\scriptstyle t \;<\; \lambda\,$
CF	$\scriptstyle \left(1 \,-\, \frac{it}{\lambda}\right)^{-k}\,$

The Erlang distribution is a two parameter family of continuous probability distributions with support $x \;\in\; (0,\, \infty)$ . The two parameters are:

a positive integer 'shape' $k$
a positive real 'rate' $\lambda$ ; sometimes the scale $\mu$ , the inverse of the rate is used.

The Erlang distribution with shape parameter $k$ equal to 1 simplifies to the exponential distribution. It is a special case of the Gamma distribution. It is the distribution of a sum of $k$ independent exponential variables with mean $\mu$ each.

The Erlang distribution was developed by A. K. Erlang to examine the number of telephone calls which might be made at the same time to the operators of the switching stations. This work on telephone traffic engineering has been expanded to consider waiting times in queueing systems in general. The distribution is now used in the fields of stochastic processes and of biomathematics.

Characterization

Probability density function

The probability density function of the Erlang distribution is

f(x; k,\lambda)={\lambda^k x^{k-1} e^{-\lambda x} \over (k-1)!}\quad\mbox{for }x, \lambda \geq 0,

The parameter k is called the shape parameter, and the parameter $\lambda$ is called the rate parameter.

An alternative, but equivalent, parametrization uses the scale parameter $\mu$ , which is the reciprocal of the rate parameter (i.e., $\mu = 1/\lambda$ ):

f(x; k,\mu)=\frac{ x^{k-1} e^{-\frac{x}{\mu}} }{\mu^k (k-1)!}\quad\mbox{for }x, \mu \geq 0.

When the scale parameter $\mu$ equals 2, the distribution simplifies to the chi-squared distribution with 2k degrees of freedom. It can therefore be regarded as a generalized chi-squared distribution for even numbers of degrees of freedom.

Because of the factorial function in the denominator, the Erlang distribution is only defined when the parameter k is a positive integer. In fact, this distribution is sometimes called the Erlang-k distribution (e.g., an Erlang-2 distribution is an Erlang distribution with k = 2). The gamma distribution generalizes the Erlang distribution by allowing k to be any real number, using the gamma function instead of the factorial function.

Cumulative distribution function (CDF)

The cumulative distribution function of the Erlang distribution is

F(x; k,\lambda) = \frac{\gamma(k, \lambda x)}{(k-1)!},

where $\gamma()$ is the lower incomplete gamma function. The CDF may also be expressed as

F(x; k,\lambda) = 1 - \sum_{n=0}^{k-1}\frac{1}{n!}e^{-\lambda x}(\lambda x)^n.

Properties

The Erlang distribution is a solution of the following differential equation:

$x f'(x) + ( \lambda x + 1 - k ) f(x) = 0$

with initial condition $f(1)=\frac{e^{-\lambda } \lambda^k}{\Gamma (k)}$ (the Poisson distribution).

Median

An asymptotic expansion is known for the median of an Erlang distribution,^[1] for which coefficients can be computed and bounds are known.^[2]^[3] An approximation is $\dfrac{k}{\lambda}\left(1-\dfrac{1}{3k+0.2}\right)$ , i.e. below the mean $\tfrac{k}{\lambda}$ .^[4]

Generating Erlang-distributed random numbers

Erlang-distributed random numbers can be generated from uniform distribution random numbers ( $U \in (0,1]$ ) using the following formula:^[5]

E(k,\lambda) \approx -\frac{1}\lambda \ln \prod_{i=1}^k U_{i}

Occurrence

Waiting times

Events that occur independently with some average rate are modeled with a Poisson process. The waiting times between k occurrences of the event are Erlang distributed. (The related question of the number of events in a given amount of time is described by the Poisson distribution.)

The Erlang distribution, which measures the time between incoming calls, can be used in conjunction with the expected duration of incoming calls to produce information about the traffic load measured in erlangs. This can be used to determine the probability of packet loss or delay, according to various assumptions made about whether blocked calls are aborted (Erlang B formula) or queued until served (Erlang C formula). The Erlang-B and C formulae are still in everyday use for traffic modeling for applications such as the design of call centers.

It has also been used in business economics for describing interpurchase times.^[6]

There are also two other Erlang distributions, both used in modeling traffic:

Erlang B distribution: this is the easier of the two, and can be used, for example, in a call centre to calculate the number of trunks one need to carry a certain amount of phone traffic with a certain "target service".

Erlang C distribution: this formula is much more difficult and is often used, for example, to calculate how long callers will have to wait before being connected to a human in a call centre or similar situation.

Stochastic processes

The Erlang distribution is the distribution of the sum of k independent and identically distributed random variables each having an exponential distribution. The long-run rate at which events occur is the reciprocal of the expectation of $X$ , that is $\lambda/k$ . The (age specific event) rate of the Erlang distribution is, for $k>1$ , monotonic in $x$ , increasing from zero at $x=0$ , to $\lambda$ as $x$ tends to infinity.^[7]

Related distributions

If $\scriptstyle X \;\sim\; \mathrm{Erlang}(k,\, \lambda)\,$ then $\scriptstyle a \cdot X \;\sim\; \mathrm{Erlang}\left(k,\, \frac{\lambda}{a}\right)\,$ with $\scriptstyle a \in \mathbb{R}$
$\scriptstyle \lim_{k \to \infty}\frac{1}{\sigma_k}\left(\mathrm{Erlang}(k,\, \lambda) \,-\, \mu_k\right) \;\xrightarrow{d}\; N(0,\, 1) \,$ (normal distribution)
If $\scriptstyle X \;\sim\; \mathrm{Erlang}(k_1,\, \lambda)\,$ and $\scriptstyle Y \;\sim\; \mathrm{Erlang}(k_2,\, \lambda)\,$ then $\scriptstyle X \,+\, Y \;\sim\; \mathrm{Erlang}(k_1 \,+\, k_2,\, \lambda)\,$
If $\scriptstyle X_i \;\sim\;$ Exponential(λ) then $\scriptstyle \sum_{i=1}^k{X_i} \;\sim\; \mathrm{Erlang}(k,\, \lambda)\,$
If k is an integer: $\scriptstyle X \;\sim\; \Gamma(k,\, \lambda )$ (gamma distribution) then $\scriptstyle X \;\sim\; \mathrm{Erlang}(k,\, \lambda)\,$
If $\scriptstyle U \;\sim\; \mathrm{Exponential}(\lambda)\,$ and $\scriptstyle V \;\sim\; \mathrm{Erlang}(n,\, \lambda)\,$ then $\scriptstyle \frac{U}{V} \;\sim\; \mathrm{Pareto}(1,\, n)$
The Erlang distribution is a special case of the Pearson type III distribution
The chi-squared distribution is a special case of the Erlang distribution.

Notes

↑ Choi, K. P. (1994). "On the medians of gamma distributions and an equation of Ramanujan". Proceedings of the American Mathematical Society 121: 245–251. doi:10.1090/S0002-9939-1994-1195477-8. JSTOR 2160389.
↑ Adell, J. A.; Jodrá, P. (2007). "On a Ramanujan equation connected with the median of the gamma distribution". Transactions of the American Mathematical Society 360 (7): 3631. doi:10.1090/S0002-9947-07-04411-X.
↑ Jodrá, P. (2012). "Computing the Asymptotic Expansion of the Median of the Erlang Distribution". Mathematical Modelling and Analysis 17 (2): 281–292. doi:10.3846/13926292.2012.664571.
↑ Banneheka BMSG, Ekanayake GEMUPD (2009) "A new point estimator for the median of gamma distribution". Viyodaya J Science, 14:95-103
↑ http://www.xycoon.com/erlang_random.htm
↑ C. Chatfield and G.J. Goodhardt: “A Consumer Purchasing Model with Erlang Interpurchase Times”; Journal of the American Statistical Association, Dec. 1973, Vol.68, pp.828-835
↑ Cox, D.R. (1967) Renewal Theory, p20, Methuen.

References

Ian Angus "An Introduction to Erlang B and Erlang C", Telemanagement #187 (PDF Document - Has terms and formulae plus short biography)

External links

Probability distributions

List of probability distributions

Discrete univariate with finite support	Benford Bernoulli Beta-binomial binomial categorical hypergeometric Poisson binomial Rademacher discrete uniform Zipf Zipf–Mandelbrot

Discrete univariate with infinite support	beta negative binomial Borel Conway–Maxwell–Poisson discrete phase-type Delaporte extended negative binomial Gauss–Kuzmin geometric logarithmic negative binomial parabolic fractal Poisson Skellam Yule–Simon zeta

Continuous univariate supported on a bounded interval	Arcsine ARGUS Balding–Nichols Bates Beta Beta rectangular Irwin–Hall Kumaraswamy logit-normal Noncentral beta raised cosine Reciprocal Triangular U-quadratic uniform Wigner semicircle

Continuous univariate supported on a semi-infinite interval	Benini Benktander 1st kind Benktander 2nd kind Beta prime Burr chi-squared chi Dagum Davis exponential-logarithmic Erlang exponential F folded normal Flory-Schulz Fréchet Gamma Gamma/Gompertz generalized inverse Gaussian Gompertz half-logistic half-normal Hotelling's T-squared hyper-Erlang hyperexponential hypoexponential inverse chi-squared scaled inverse chi-squared inverse Gaussian inverse gamma Kolmogorov Lévy log-Cauchy log-Laplace log-logistic log-normal matrix-exponential Maxwell–Boltzmann Maxwell–Jüttner Mittag-Leffler Nakagami noncentral chi-squared Pareto phase-type Poly-Weibull Rayleigh relativistic Breit–Wigner Rice shifted Gompertz truncated normal type-2 Gumbel Weibull Wilks's lambda

Continuous univariate supported on the whole real line	Cauchy exponential power Fisher's z generalized normal generalized hyperbolic geometric stable Gumbel Holtsmark hyperbolic secant Johnson S_U Landau Laplace asymmetric Laplace logistic noncentral t normal (Gaussian) normal-inverse Gaussian skew normal slash stable Student's t type-1 Gumbel Tracy–Widom variance-gamma Voigt

Continuous univariate with support whose type varies	generalized extreme value generalized Pareto Tukey lambda q-Gaussian q-exponential q-Weibull shifted log-logistic

Mixed continuous-discrete univariate	rectified Gaussian

Multivariate (joint)	Discrete Ewens multinomial Dirichlet-multinomial negative multinomial Continuous Dirichlet generalized Dirichlet multivariate normal multivariate stable multivariate t normal-inverse-gamma normal-gamma Matrix-valued inverse matrix gamma inverse-Wishart matrix normal matrix t matrix gamma normal-inverse-Wishart normal-Wishart Wishart

Directional	Univariate (circular) directional Circular uniform univariate von Mises wrapped normal wrapped Cauchy wrapped exponential wrapped asymmetric Laplace wrapped Lévy Bivariate (spherical) Kent Bivariate (toroidal) bivariate von Mises Multivariate von Mises–Fisher Bingham

Degenerate and singular	Degenerate Dirac delta function Singular Cantor

Families	Circular compound Poisson elliptical exponential natural exponential location-scale maximum entropy mixture Pearson Tweedie wrapped

This article is issued from Wikipedia - version of the Saturday, March 19, 2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.