Identification of gene modules using a generative model for relational data

This thesis presents generative models for two types of relational data (edge rankings and networks) from block structures, based on Brumm et al (2008) [1]. We design and implement a set of inference algorithms, and evaluate them on real as well as simulated data. We conclude with a discussion of how well the real data fits the model, and with various extensions of the basic model. Revision: ubcdiss.cls r27