Syllabus

Module 1. Classical Linear Regression 


  • Ordinary Least Squares (OLS)
  • Estimation
  • BLUE, Gauss-Markov Theorem
  • Confidence
  • Confidence Interval for a single Linear Parametric Function (LPF)
  • Confidence Regions for multiple LPFs
  • Simultaneous Confidence Intervals for multiple LPFs
  • Prediction Interval
  • Hypothesis Testing
  • Testing for the significance of a single LPF
  • Testing for the significance of individual predictors: t-test
  • ANOVA Table and testing hypothesis involving several LPFs
  • Testing for the significance of the entire model/testing for lack of fit: F-test
  • Categorical Predictors, Interaction models
  • Least Squares in Heteroskedastic Models
  • Generalized Least Squares
  • Weighted Least Squares
  • Residual Diagnostics


Additional Readings:
  • Read chapter 12 of PRA by J. Faraway for a complete linear regression example 
  • tidyverse from ModernDive for reducing unstructured data to a regression framework. 

Module 2. Beyond Least Squares


  • Non-Linear Regression
  • Transforming the Response: Box-Cox method
  • Transforming the Predictors
  • Polynomial Regression
  • Regression Splines*
  • Local Regression
  • Generalized Additive Models (GAM)
  • Bootstrapping methods

  • Additional Readings: 
  • Ch 6 slides from ISLR for more information on the above methods 
  • Ch 5 slides from ISLR for cross validation and bootstrap

  • Robust Regression
  • Quantile Regression
  • M-Estimation
  • Huber loss, Robustness and rlm R package