Statistical Learning Methods.

Catalog description

This course will describe, implement and compare statistical models for classification and regression problems including ordinary least squares regression, logistic regression, K-nearest neighbors, shrinkage methods, decision trees, random forests, clustering algorithms, principal component analysis, neural networks, random walks, and autoregressive models. Common methods for the selection and validation of models such as stepwise selection, cross-validation, training/testing sets and data visualization will also be discussed. The use of statistical software will be emphasized. An introductory background in programming is recommended. Prerequisites: MATH 037 , DATA 051 , or MATH 131 with a “C-“ or better or permission of instructor.