Inverse Gaussian distribution

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search
Inverse Gaussian
Probability density function
PDF invGauss.svg
CDF where is the standard normal (standard Gaussian) distribution c.d.f.
Ex. kurtosis

In probability theory, the inverse Gaussian distribution (also known as the Wald distribution) is a two-parameter family of continuous probability distributions with support on (0,∞).

Its probability density function is given by

for x > 0, where is the mean and is the shape parameter.[1]

As λ tends to infinity, the inverse Gaussian distribution becomes more like a normal (Gaussian) distribution. The inverse Gaussian distribution has several properties analogous to a Gaussian distribution. The name can be misleading: it is an "inverse" only in that, while the Gaussian describes a Brownian motion's level at a fixed time, the inverse Gaussian describes the distribution of the time a Brownian motion with positive drift takes to reach a fixed positive level.

Its cumulant generating function (logarithm of the characteristic function) is the inverse of the cumulant generating function of a Gaussian random variable.

To indicate that a random variable X is inverse Gaussian-distributed with mean μ and shape parameter λ we write .


Single parameter form[edit]

The probability density function (pdf) of inverse Gaussian distribution has a single parameter form given by

In this form, the mean and variance of the distribution are equal,

Also, the cumulative distribution function (cdf) of the single parameter inverse Gaussian distribution is related to the standard normal distribution by

where and where the is the cdf of standard normal distribution. The variables and are related to each other by the identity

In the single parameter form, the MGF simplifies to

An inverse Gaussian distribution in double parameter form can be transformed into a single parameter form by appropriate scaling where

The standard form of inverse Gaussian distribution is


If Xi has an distribution for i = 1, 2, ..., n and all Xi are independent, then

Note that

is constant for all i. This is a necessary condition for the summation. Otherwise S would not be inverse Gaussian.


For any t > 0 it holds that

Exponential family[edit]

The inverse Gaussian distribution is a two-parameter exponential family with natural parametersλ/(2μ2) and −λ/2, and natural statistics X and 1/X.

Relationship with Brownian motion[edit]

The stochastic process Xt given by

(where Wt is a standard Brownian motion and ) is a Brownian motion with drift ν.

Then the first passage time for a fixed level by Xt is distributed according to an inverse-Gaussian:

When drift is zero[edit]

A common special case of the above arises when the Brownian motion has no drift. In that case, parameter μ tends to infinity, and the first passage time for fixed level α has probability density function

This is a Lévy distribution with parameters and .

Maximum likelihood[edit]

The model where

with all wi known, (μλ) unknown and all Xi independent has the following likelihood function

Solving the likelihood equation yields the following maximum likelihood estimates

and are independent and

Generating random variates from an inverse-Gaussian distribution[edit]

The following algorithm may be used.[2]

Generate a random variate from a normal distribution with a mean of 0 and 1 standard deviation

Square the value

and use this relation

Generate another random variate, this time sampled from a uniform distribution between 0 and 1

If then return else return

Sample code in Java:

public double inverseGaussian(double mu, double lambda) {
       Random rand = new Random();
       double v = rand.nextGaussian();   // sample from a normal distribution with a mean of 0 and 1 standard deviation
       double y = v*v;
       double x = mu + (mu*mu*y)/(2*lambda) - (mu/(2*lambda)) * Math.sqrt(4*mu*lambda*y + mu*mu*y*y);
       double test = rand.nextDouble();  // sample from a uniform distribution between 0 and 1
       if (test <= (mu)/(mu + x))
              return x;
              return (mu*mu)/x;
Wald distribution using Python with aid of matplotlib and NumPy

And to plot Wald distribution in Python using matplotlib and NumPy:

import matplotlib.pyplot as plt
import numpy as np

h = plt.hist(np.random.wald(3, 2, 100000), bins=200, normed=True)

Related distributions[edit]

  • If , then for any number [3]
  • If then
  • If for then
  • If then

The convolution of an inverse Gaussian distribution (a Wald distribution) and an exponential (an ex-Wald distribution) is used as a model for response times in psychology,[4] with visual search as one example.[5]


This distribution appears to have been first derived by Erwin Schrödinger in 1915 as the time to first passage of a Brownian motion.[6] The name inverse Gaussian was proposed by Tweedie in 1945.[7] Abraham Wald re-derived this distribution in 1947 as the limiting form of a sample in a sequential probability ratio test. Maurice Tweedie investigated this distribution in 1957 and established some of its statistical properties.

Numeric computation and software[edit]

Despite the simple formula for the probability density function, numerical probability calculations for the inverse Gaussian distribution nevertheless require special care to achieve full machine accuracy in floating point arithmetic for all parameter values.[8] Functions for the inverse Gaussian distribution are provided for the R programming language by the statmod package,[9] available from the Comprehensive R Archive Network (CRAN).

See also[edit]


  1. ^ Chhikara, Raj; Folks, Leroy (1989). The inverse Gaussian distribution: theory, methodology and applications. New York: Marcel Dekker. ISBN 978-0-8247-7997-9.
  2. ^ Michael, John R.; Schucany, William R.; Haas, Roy W. (May 1976). "Generating Random Variates Using Transformations with Multiple Roots". The American Statistician. 30 (2): 88–90. doi:10.2307/2683801. JSTOR 2683801.
  3. ^ Chhikara, Raj; Folks, Leroy (1989). The inverse Gaussian distribution: theory, methodology and applications. New York: Marcel Dekker. ISBN 978-0-8247-7997-9.
  4. ^ Schwarz, W (2001). "The ex-Wald distribution as a descriptive model of response times". Behavior Research Methods, Instruments, and Computers. 33 (4): 457–69. doi:10.3758/bf03195403. PMID 11816448.
  5. ^ Palmer, E. M.; Horowitz, T. S.; Torralba, A.; Wolfe, J. M. (2011). "What are the shapes of response time distributions in visual search?". Journal of Experimental Psychology: Human Perception and Performance. 37 (1): 58–71. doi:10.1037/a0020747. PMC 3062635. PMID 21090905.
  6. ^ Schrödinger, E. (1915). "Zur Theorie der Fall-und Steigversuche an Teilchen mit Brownscher Bewegung". Physikalische Zeitschrift. 16: 289–295.
  7. ^ Folks, J. L.; Chhikara, R. S. (1978). "The Inverse Gaussian Distribution and Its Statistical Application—A Review". Journal of the Royal Statistical Society. Series B (Methodological). 40 (3): 263–289. doi:10.2307/2984691 (inactive 2018-09-11). JSTOR 2984691.
  8. ^ Giner, Goknur; Smyth, Gordon (August 2016). "statmod: Probability Calculations for the Inverse Gaussian Distribution". The R Journal. 8 (1): 339–351. arXiv:1603.06687. Bibcode:2016arXiv160306687G.
  9. ^ "statmod: Statistical Modeling".

Further reading[edit]

External links[edit]