Perfectly random sampling of truncated multinormal distributions

被引:8
作者
Fernandez, Pedro J. [1 ]
Ferrari, Pablo A. [2 ]
Grynberg, Sebastian P. [3 ]
机构
[1] Fundacao Getulio Vargas, BR-22631050 Rio De Janeiro, Brazil
[2] Univ Sao Paulo, Inst Matemat & Estatist, BR-05311970 Sao Paulo, Brazil
[3] Univ Buenos Aires, Fac Ingn, Dept Matemat, RA-1063 Buenos Aires, DF, Argentina
关键词
perfect sampling; simulation; normal distribution;
D O I
10.1239/aap/1198177235
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
The target measure mu is the distribution of a random vector in a box B, a Cartesian product of bounded intervals. The Gibbs sampler is a Markov chain with invariant measure mu. A 'coupling from the past' construction of the Gibbs sampler is used to show ergodicity of the dynarnics and to perfectly simulate mu. An algorithm to sample vectors with multinormal distribution truncated to B is then implemented.
引用
收藏
页码:973 / 990
页数:18
相关论文
共 15 条
[1]  
Allenby GM, 1999, J ECONOMETRICS, V89, P57
[2]  
[Anonymous], 1987, MULTIPLE IMPUTATIONS
[3]   SAMPLING-BASED APPROACHES TO CALCULATING MARGINAL DENSITIES [J].
GELFAND, AE ;
SMITH, AFM .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1990, 85 (410) :398-409
[4]   STOCHASTIC RELAXATION, GIBBS DISTRIBUTIONS, AND THE BAYESIAN RESTORATION OF IMAGES [J].
GEMAN, S ;
GEMAN, D .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (06) :721-741
[5]  
GEWEKE J, 1991, COMPUTING SCIENCE AND STATISTICS, P571
[6]   Statistical inference in the multinomial multiperiod probit model [J].
Geweke, JF ;
Keane, MP ;
Runkle, DE .
JOURNAL OF ECONOMETRICS, 1997, 80 (01) :125-165
[7]   Perfect simulation of conditionally specified models [J].
Moller, J .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1999, 61 :251-264
[8]   Exact sampling from a continuous state space [J].
Murdoch, DJ ;
Green, PJ .
SCANDINAVIAN JOURNAL OF STATISTICS, 1998, 25 (03) :483-502
[9]  
Propp JG, 1996, RANDOM STRUCT ALGOR, V9, P223, DOI 10.1002/(SICI)1098-2418(199608/09)9:1/2<223::AID-RSA14>3.0.CO
[10]  
2-O