High-Dimensional High-Throughput Data Analysis ((3 Units))

Catalog description

Prerequisite: Regression and ANOVA and statistical data management, or instructor's permission. This course provides exposure to a variety of advanced statistical methods (beyond the ones taught in our undergraduate curriculum) for handling the challenges of high-dimensional high-throughput data, along with their software implementation and applications. Topics include multiple hypothesis testing and multiplicity adjustment, curse of dimensionality, sparsity, high-dimensional data visualization, dimension reduction methods, model selection and estimator selection, machine learning methods, aggregation of estimators and classifiers, graphical and network models. (Formerly 3470:594)