Biostatistics Seminar Series - Tanya P. Garcia, PhD

Title: c2pLasso: the Categorical-Continuous Pliable Lasso to Identify Brain Regions Affecting Motor Impairment in Huntington DiseaseAbstract: In many clinical studies, parsimonious prediction models with informative predictors are essential for forecasting and monitoring the progression of a disease. Developing such prediction models is a challenge when the relationship between the predictors and the response depends on other structured modifying variables such as categorical variables. We formalize this problem as the varying-coefficient model selection and propose a novel variable selection method to account for both continuous and categorical modifying variables. Our contributions are three-fold. Our method is empirically shown to better screen irrelevant variables over the existing method that ignores the group structure of categorical modifying variables. Also, our method is designed not only for categorical modifying variables but also for other group-structured modifying variables. Last, our method screens irrelevant variables better than the existing method even for continuous modifying variables. With all these features, our method provides us with a prediction model with higher specificity, lower false discovery rate and lower mean squared error than the existing method. The proposed methodology is motivated by and illustrated using data from a Huntington disease study; the result identifies brain regions associated with motor impairment accounting for differentiated relationship by disease severity. To the best of our knowledge, our study is the first to identify the interaction effect between disease severity and the volume of brain regions in a varying-coefficient model framework.