Journal of the Korean Data and Information Science Society

The Korean Data and Information Science Society (한국데이터정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Performance comparison of random number generators based on Adaptive Rejection Sampling

적응 기각 추출을 기반으로 하는 난수 생성기의 성능 비교

  • Kim, Hyotae (Department of Statistics, Korea University) ;
  • Jo, Seongil (Department of Statistics, Korea University) ;
  • Choi, Taeryon (Department of Statistics, Korea University)
  • Received : 2015.02.24
  • Accepted : 2015.04.09
  • Published : 2015.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Adaptive Rejection Sampling (ARS) method is a well-known random number generator to acquire a random sample from a probability distribution, and has the advantage of improving the proposal distribution during the sampling procedures, which update it closer to the target distribution. However, the use of ARS is limited since it can be used only for the target distribution in the form of the log-concave function, and thus various methods have been proposed to overcome such a limitation of ARS. In this paper, we attempt to compare five random number generators based on ARS in terms of adequacy and efficiency. Based on empirical analysis using simulations, we discuss their results and make a comparison of five ARS-based methods.

적응 기각 추출 (adaptive rejection sampling)방법은 특정한 형태의 확률분포로 부터 확률표본을 추출하기 위한 대표적인 난수생성기 (random number generator)로서, 추출된 표본으로부터 제안분포 (proposal distribution)가 개선이 되는 장점을 가지고 있다. 그러나, 기존에 제안된 적응기각추출 방법은 확률분포의 형태가 로그-오목 함수 (log-concave function)인 경우에만 사용이 가능하기 때문에 적용범위가 제한적이다. 최근의 연구결과에서는, 이러한 단점을 보완하기 위해 다양한 형태의 적응기각추출이 진행되고 있으며, 이에 본 논문에서는 기존의 적응기각추출 방법을 포함한 총 5가지의 난수 생성 방법에 대해서 고찰하고, 아울러 모의실험을 통해 각 방법들간의 성능에 대하여, 적합성과 효율성의 관점에서 실증적으로 비교 분석하도록 한다.

Keywords

References

  1. Choi, S. M., Kim, D. H., Shin, I. H., Kim, H. G. and Kim, S. G. (2011). Robust Bayesian meta analysis. Journal of the Korean Data & Information Science Society, 22, 459-466.
  2. Choi, C. H. and Ko, B. W. (2014). Stochastic simulation of daily precipitation: A copula approach. Journal of the Korean Data & Information Science Society, 25, 245-254. https://doi.org/10.7465/jkdi.2014.25.1.245
  3. Evans, M. and Swartz, T. (1998). Random variable generation using concavity properties of transformed densities. Journal of Computational and Graphical Statistics, 7, 514-528.
  4. Gilks, W. R., Best, N. G. and Tan, K. K. C. (1995). Adaptive rejection Metropolis sampling within Gibbs Sampling. Journal of the Royal Statistical Society : Series C (Applied Statistics), 44, 455-472.
  5. Gilks, W. R. and Wild, P. (1992). Adaptive rejection sampling for Gibbs sampling. Journal of the Royal Statistical Society : Series C (Applied Statistics), 41, 337-348.
  6. Givens, G. H. and Hoeting, J. A. (2013). Computational Statistics, 2nd ed., Wiley Series in Computational Statistics, John Wiley & Sons, Inc., New Jersey.
  7. Gorur, D. and Teh, Y. W. (2011). Concave-Convex adaptive rejection sampling. Journal of Computational and Graphical Statistics, 20, 670-691. https://doi.org/10.1198/jcgs.2011.09058
  8. Martino, L. and Miguez, J. (2011). A generalization of the adaptive rejection sampling algorithm. Statistics and Computing, 21, 633-647. https://doi.org/10.1007/s11222-010-9197-9
  9. Mo, E. B. and Park, C. S. (2013). Application of quasi-Monte Carlo methods in multi-asset option pricing. Journal of the Korean Data & Information Science Society, 24, 669-677. https://doi.org/10.7465/jkdi.2013.24.4.669
  10. Park, K. Y., Kwon, G. C. and Kwon, Y. D. (1998). Uniformity and independency tests of pseudo-random number generators. Journal of the Korean Data & Information Science Society, 9, 237-246.
  11. Sohn, J. K., Kim, H. J. and Kang, S. G. (1996). Convergence diagnostics for the Gibbs sampler. Journal of Statistical Theory & Methods, 7, 1-12.

Cited by

  1. Density estimation of summer extreme temperature over South Korea using mixtures of conditional autoregressive species sampling model vol.27, pp.5, 2016, https://doi.org/10.7465/jkdi.2016.27.5.1155