Lesson 4: Variable Selection


Upon successful completion of this lesson, you should be able to:

  • Practice best subset selection and stepwise selection for reducing the number of predictor variables in regression focusing on prediction.
  • Assess the predictive ability of the model developed in training data in test data.
  • Indirectly estimate test error by adjusting training error to account for bias due to overfitting (Cp, AIC, BIC, adjusted R2).
  • Directly estimate test error using the validation set approach or cross-validation approach.