We construct Markov chain algorithms for sampling from discrete exponential families conditional on a sufficient statistic. Examples include contingency tables, logistic regression, and spectral analysis of permutation data. The algorithms involve computations in polynomial rings using Gröbner bases.
Publié le : 1998-02-14
Classification:
Conditional inference,
Monte Carlo Markov chain,
exponential families,
Gröbner bases,
6E17,
13P10
@article{1030563990,
author = {Diaconis, Persi and Sturmfels, Bernd},
title = {Algebraic algorithms for sampling from conditional distributions},
journal = {Ann. Statist.},
volume = {26},
number = {3},
year = {1998},
pages = { 363-397},
language = {en},
url = {http://dml.mathdoc.fr/item/1030563990}
}
Diaconis, Persi; Sturmfels, Bernd. Algebraic algorithms for sampling from conditional distributions. Ann. Statist., Tome 26 (1998) no. 3, pp. 363-397. http://gdmltest.u-ga.fr/item/1030563990/