Stereotype Logit Models for High-Dimensional Data

• Activity Number: 125
• Type: Contributed
• Date/Time: Monday, August 2, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Andre Williams*+ and Kellie Archer+
• Companies: Virginia Commonwealth University and Virginia Commonwealth University
• Keywords: disease progression ; Stereotype logit ; elastic net ; gene expression

Abstract

Gene expression studies are of growing importance in the field of medicine. In fact, subtypes within the same disease have been shown to have differing gene expression profiles (Golub et al., 1999). Often rather than differentiating disease subclasses researchers are interested in differentiating the same disease by a categorical classification of disease progression. Specifically, it is likely of interest to identify genes that are associated with progression and to accurately predict the state of progression within a disease using gene expression data. We propose a method that combines the Stereotype logistic model (Anderson, 1984) with an elastic net penalty (Friedman et al. 2009), which is a combination of a ridge and lasso penalty. The proposed method will be applied to relevant data and the results will be reported.