Back To Index Previous Article Next Article Full Text


Statistica Sinica 21 (2011), 1591-1609
doi:10.5705/ss.2008.078





SAMPLING LARGE TABLES WITH CONSTRAINTS


Ian H. Dinwoodie and Yuguo Chen


Portland State University and University of Illinois at Urbana-Champaign


Abstract: We describe a new sequential sampling method for constrained multi-way tables, with foundations in linear programming and sequential normal sampling. The method builds on techniques from other sequential algorithms in a way that scales well and can handle more challenging data sets. We apply the new algorithm to data to demonstrate its efficiency.



Key words and phrases: Conditional inference, contingency table, exact test, hypergeometric distribution, importance sampling, multivariate normal distribution, sequential sampling.

Back To Index Previous Article Next Article Full Text