Dynamic Markov Bases
Author:
- Adrian DobraADAdrian Dobra
- 14 February 2012
- journal article
- algorithmic novelties
- Published by Taylor & Francis in Journal of Computational and Graphical Statistics
- Vol. 21 (2) , 496-517
Abstract
This article presents a computational approach for generating Markov bases for multiway contingency tables whose cell counts might be constrained by fixed marginals and by lower and upper bounds. Our framework includes tables with structural zeros as a particular case. Instead of computing the entire Markov bases in an initial step, our framework finds sets of local moves that connect each table in the reference set with a set of neighbor tables. We construct a Markov chain on the reference set of tables that requires only a set of local moves at each iteration. The union of these sets of local moves forms a dynamic Markov basis. We illustrate the practicality of our algorithms in the estimation of exact p-values for a three-way table with structural zeros and a sparse eight-way table. This article has online supplementary materials.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Sampling large tables with constraintsStatistica Sinica, 2011
- Markov bases and subbases for bounded contingency tablesAnnals of the Institute of Statistical Mathematics, 2010
- Conditional Inference on Tables With Structural ZerosJournal of Computational and Graphical Statistics, 2007
- Data augmentation in multi-way contingency tables with fixed marginal totalsJournal of Statistical Planning and Inference, 2006
- Markov bases and structural zerosJournal of Symbolic Computation, 2006
- Sequential importance sampling for multiway tablesThe Annals of Statistics, 2006
- Sequential Monte Carlo Methods for Statistical Analysis of TablesJournal of the American Statistical Association, 2005
- Ecological Inference for 2 × 2 TablesJournal of the Royal Statistical Society Series A: Statistics in Society, 2004
- An importance sampling algorithm for exact conditional tests in log-linear modelsBiometrika, 1999
- A Warning on the Use of Chi-Squared Statistics with Frequency Tables with Small Expected Cell CountsJournal of the American Statistical Association, 1988