A modern course in multivariate statistics. Elements of classical multivariate analysis as needed, including multivariate normal and Wishart distributions. Clustering; principal component analysis. Model selection and evaluation; prediction error; variable selection; stepwise regression; regularized regression. Cross-validation. Classification; linear discriminant analysis. Tree-based methods. Time permitting, optional topics may include nonparametric density estimation, multivariate regression, support vector machines, and random forests.
Prerequisite: CSE 131; Math 233; Math 309 or Math 429; multivariable-calculus-based probability and mathematical statistics (Math/SDS 493-494 or Math/SDS 3211/4211); Math/SDS 439. Prior knowledge of R at the level introduced in Math/SDS 439 is assumed.
Course Attributes: AS NSM
