Generating gamma variates by a modified rejection technique

@article{Ahrens1982GeneratingGV,
  title={Generating gamma variates by a modified rejection technique},
  author={Joachim H. Ahrens and Ulrich Dieter},
  journal={Commun. ACM},
  year={1982},
  volume={25},
  pages={47-54}
}
A suitable square root transformation of a gamma random variable with mean a ≥ 1 yields a probability density close to the standard normal density. A modification of the rejection technique then begins by sampling from the normal distribution, being able to accept and transform the initial normal observation quickly at least 85 percent of the time (95 percent if a ≥ 4). When used with efficient subroutines for sampling from the normal and exponential distributions, the resulting accurate method… 

Figures and Tables from this paper

Generating Student’s T Variates by a Modified Rejection Method

A new algorithm for sampling from Student’s ta distributions with parameter a > 3 is presented. The method is based on a modified acceptance-rejection technique introduced in 1981 by J.H. Ahrens for

Logarithmic Transformation-Based Gamma Random Number Generators

Developing efficient gamma variate generators is important for Monte Carlo methods. With a brief review of existing methods for generating gamma random numbers, this article proposes two simple gamma

Computer Generation of Poisson Deviates from Modified Normal Distributions

Using efficient subprograms for generating uniform, exponential, alid normal deviates, the new algorithm is much faster than all competing methods.

Generating gamma variates

An algorithm to generate variates having a gamma distribution with shape parameter greater than one is presented, which is faster than Schmeiser and Lal's G4PE, yet is equally simple and easy to implement.

Efficient table-free sampling methods for the exponential, Cauchy, and normal distributions

Three algorithms for sampling from exponential, Cauchy and normal distributions are developed. They are based on the "exact approximation" method, and their expected numbers of consumed uniform

Generating random numbers from a distribution specified by its Laplace transform

This paper advocates simulation by the inversion method using a modified Newton-Raphson method, with values of the distribution and density functions obtained by numerical transform inversion, and shows that this algorithm performs well in a series of increasingly complex examples.

Random variate generation for exponentially and polynomially tilted stable distributions

This work develops exact random variate generators for the polynomially and exponentially tilted unilateral stable distributions and presents a novel double rejection method that is useful whenever densities have an integral representation involving an auxiliary variable.

Simulating theta random variates

Gamma Pseudo Random Number Generators

This article describes the existing algorithms for the generation of (independent and identically distributed-i.i.d.-) Gamma distribution values as well as the theoretical and mathematical foundations that support their validity.

Two New Ratio-of-Uniforms Gamma Random Number Generators

Two simple algorithms to generate gamma random numbers are proposed in this article. Both algorithms use the ratio-of-uniforms method and are based on logarithmic transformations of the gamma random
...

References

SHOWING 1-10 OF 27 REFERENCES

The Computer Generation of Beta, Gamma and Normal Random Variables

Timing comparisons on two computers show that the resulting algorithms are appreciably faster than any previously published, except for the gamma distribution with small or small integer index.

Acceptance-Rejection Techniques for Sampling from The Gamma and Beta Distributions.

Abstract : John von Neumann's idea of sampling from a distribution by majorizing its probability density function is applied to gamma and beta distributions. Optimum envelopes are constructed

A survey of methods for sampling from the gamma distribution

The current state of the art in gamma random variate generation is surveyed including the leading algorithms of Ahrens and Dieter, Atkinson, Cheng, Fishman, Marsaglia, Tadikamalla and Wallace.

On computer generation of gamma random variables by rejection and composition procedures 2

Various algorithms for generating gamma random variables, by combining rejection and composition procedures, are presented, for the case when the parameter of the gamma distribution is 0<v<l.

Computer generation of gamma random variables

A new method for generating random variables from the gamma distribution with nonintegral shape parameter α is proposed. This method is similar to two other methods recently given by Wallace and

Computer Generation of Random Variables Using the Ratio of Uniform Deviates

The ratio-of-uniforms method for generating random variables having continuous nonuniform distributions is presented and can be used for generating short and often as fast algorithms as well as longer algorithms.

Sampling from the gamma distribution on a computer

This paper describes a method of generating gamma variates that appears to be less costly than Wallace's recently suggested method, and which also dominates methods recently suggested by Dieter and Ahrens.

An Easily Programmed Algorithm for Generating Gamma Random Variables

An easily programmed algorithm for generating gamma random variables with index ax greater than one which is intended to be complementary to the algorithms GO of Ahrens and Dieter and GB of Cheng and Fishman is described and compared with these algorithms.

The squeeze method for generating gamma variates

The Generation of Gamma Variables with Non‐Integral Shape Parameter

A rejection method is described for generating exact gamma variates with shape parameter α, where α > 1. The method is compared with previously published methods in terms of speed and program