Simulating from a gamma distribution with small shape parameter
Computation
2015-04-08 v3 Statistics Theory
Statistics Theory
Abstract
Simulating from a gamma distribution with small shape parameter is a challenging problem. Towards an efficient method, we obtain a limiting distribution for a suitably normalized gamma distribution when the shape parameter tends to zero. Then this limiting distribution provides insight to the construction of a new, simple, and highly efficient acceptance--rejection algorithm. Comparisons based on acceptance rates show that the proposed procedure is more efficient than existing acceptance--rejection methods.
Cite
@article{arxiv.1302.1884,
title = {Simulating from a gamma distribution with small shape parameter},
author = {Chuanhai Liu and Ryan Martin and Nick Syring},
journal= {arXiv preprint arXiv:1302.1884},
year = {2015}
}
Comments
7 pages, 2 figures