Duke University - Institute of Statistics & Decision Sciences
I will discuss aspects of data analysis and modelling arising from a number of clinical studies that aim to integrate gene expression, and other forms of molecular data, into predictive modelling of clinical outcomes and disease states. Some of our work on empirical and model based approaches to defining underlying factor structure in large-scale expression data, and the use of estimated factors in predictive regression and classification tree models, will be reviewed. One particular Bayesian approach to predictive tree modelling will be described in more detail, and exemplified in analyses from these clinical studies. I'll also touch on a number of conceptual, technical and practical issues, and current areas of development.