CS700:Graduate Seminar in Computer Science & Informatics

Estimation of a semiparametric mixture of regression models: application to the ChipMIX model
Pierre VANDEKERKHOVE
Department of Analysis and Applied Mathematics, University Paris-Est Marne-la-Vallée
Visiting professor, Department of Materials Science and Engineering, Georgia Institute of Technology

In this talk we will present a new mixture of regression models which is a generalization of the semiparametric two-component mixture model, which can be used as an exploratory and complementary tool for the modeling of two-color ChIP-chip datasets. An implementation and numerical performances for this method is discussed, using several simulated datasets and one real microarray dataset, the ChipMIX model.