Abstract
The perfect sampling method of Kijima and Matsui (2006) for 2× K contingency tables is extended to 2 × ⋯ × 2 × K tables. Based on this, a Metropolis sampling method is then proposed to implement Zelen's homogeneity test. Finally, an application is shown on gene expression data where cancer samples are compared to non-cancer samples across various tissues.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have