Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1147867 | Journal of Statistical Planning and Inference | 2010 | 14 Pages |
Abstract
We consider conditional exact tests of factor effects in designed experiments for discrete response variables. Similarly to the analysis of contingency tables, a Markov chain Monte Carlo method can be used for performing exact tests, when large-sample approximations are poor and the enumeration of the conditional sample space is infeasible. For designed experiments with a single observation for each run, we formulate log-linear or logistic models and consider a connected Markov chain over an appropriate sample space. In particular, we investigate fractional factorial designs with 2p-q runs, noting correspondences to the models for 2p-q contingency tables.
Related Topics
Physical Sciences and Engineering
Mathematics
Applied Mathematics
Authors
Satoshi Aoki, Akimichi Takemura,