Basic Information
The Course Contains Two Parts. The First Part Deals With A Mis-specified Linear Model and The Second Is About High-dimensional Regression. Topics# Best Linear Predictor, Least Squares, Gauss-markov Theorem, Asymptotic Distribution, Model Selection in Low And High Dimensions, Ridge Estimator, Existence Theorem, Lasso, Error Bound For Lasso. Learning Outcomes# At The End of The Course The Student Should 1. Be Familiar With The Basic Theory of Least Squares Estimates Both In Linear and Non-linear Scenarios. 2. Use Standard Software in Order to Compute Least Squares Estimates, Confidence Intervals and Hypothesis Testing. 3. Program Different Statistical Methods and Compare Them Using Simulations. 4. Be Familiar With The Basic Theory of Model Selection in Regression As Well As Ridge and Lasso Estimates. 5. Use Standard Software in Order to Compute Ridge and Lasso Estimates.
Faculty: Data and Decision Sciences
|Graduate Studies
Pre-required courses
94423 - Introduction to Statistics or 94424 - Statistics 1