Algorithm 802: an automatic generator for bivariate log-concave distributions

ABSTRACT

Different automatic (also called universal or black-box) methods have been suggested to sample from univariate log-concave distributions. Our new automatic algorithm for bivariate log-concave distributions is based on the method of transformed density rejection. In order to construct a hat function for a rejection algorithm the bivariate density is transformed by the logarithm into a concave function. Then it is possible to construct a dominating function by taking the minimum of several tangent planes, which are by exponentiation transformed back into the original scale. The choice of the points of contact is automated using adaptive rejection sampling. This means that points that are rejected by the rejection algorithm can be used as additional points of contact. The article describes the details how this main idea can be used to construct Algorithm ALC2D that can generate random pairs from all bivariate log-concave distributions with known domain, computable density, and computable partial derivatives.

REFERENCES

• 1: AHRENS, J. H. 1995. A one-table method for sampling from continuous and discrete distributions. Computing 54, 2, 127-146.
• 2: DAGPUNAR, J. 1988. Principles of Random Variate Generation. Clarendon Oxford Science Publications, Oxford, UK.
• 3: DEVROYE, L. 1986. Non-Uniform Random Variate Generation. Springer-Verlag, New York, NY.
• 4: Luc Devroye, Random variate generation for multivariate unimodal densities, ACM Transactions on Modeling and Computer Simulation (TOMACS), v.7 n.4, p.447-477, Oct. 1997 [doi>10.1145/268403.268413]
• 5: EVANS, M. AND SCHWARTZ, T. 1998. Random variable generation using concavity properties of transformed densities. J. Comput. Graph. Stat. 7, 4, 514-528.
• 6: GILKS, W. R. AND WILD, P. 1992. Adaptive rejection sampling for Gibbs sampling. Appl. Stat. 41, 2, 337-348.
• 7: Wolfgang Hörmann, A rejection technique for sampling from T-concave distributions, ACM Transactions on Mathematical Software (TOMS), v.21 n.2, p.182-193, June 1995 [doi>10.1145/203082.203089]
• 8: H RMANN, W. AND DEFLINGER, G. 1994. Universal generators for correlation induction. In Proceedings in Computational Statistics (COMPSTAT), R. Dutter and W. Grossmann, Eds. Physica-Verlag GmbH, Heidelberg, Germany, 52-57.
• 9: Mark E Johnson, Multivariate statistical simulation, John Wiley & Sons, Inc., New York, NY, 1987
• 10: Josef Leydold, A rejection technique for sampling from log-concave multivariate distributions, ACM Transactions on Modeling and Computer Simulation (TOMACS), v.8 n.3, p.254-280, July 1998 [doi>10.1145/290274.290287]
• 11: Josef Leydold , Wolfgang Hörmann, A sweep-plane algorithm for generating random tuples in simple polytopes, Mathematics of Computation, v.67 n.224, p.1617-1635, Oct. 1998 [doi>10.1090/S0025-5718-98-01004-7]
• 12: MAULDON, g. G. 1959. A generalization of the beta-distribution. Ann. Math. Stat. 30, 2, 509-520.
• 13: S. Stefănescu , I. Văduva, On computer generation of random vectors by transformation of uniformly distributed vectors, Computing, v.39 n.2, p.141-153, April 1, 1987 [doi>10.1007/BF02310103]
• 14: WAKEFIELD, J. C., GELFAND, A. E., AND SMITH, A. F. M. 1991. Efficient generation of random variates via the ratio-of-uniforms method. Stat. Comput. 1, 2, 129-133.

INDEX TERMS

Primary Classification:
  D. Software
  D.3 PROGRAMMING LANGUAGES

Additional Classification:
  G. Mathematics of Computing
  G.3 PROBABILITY AND STATISTICS
      Subjects: Random number generation

General Terms:
Algorithms

Keywords:
automatic generator, bivariate log-concave distributions, rejection method, universal generator