Webinar: Building Better Models in Multiple Regression

The typical approach to building a regression model involves the removal of terms with p-values greater than .05 or 0.1, resulting in models that are good, but not necessarily best. In this webinar, we review metrics and methods that maximize the chance of building the best possible model, with important terms kept in the model, unimportant terms removed from the model, and provide maximum prediction accuracy. SigmaXL software will be used to demonstrate these methods.

Agenda

  • Model building metrics:
    • p-values
    • Akaike Information Criteria (AICc)
    • Bayesian Information Criteria (BIC)
  • Automatic model building methods:
    • Forward Selection
    • Backward Elimination
    • Mixed Forward/Backward
    • Best Subsets
  • Validation of models:
    • Predicted R-Square
    • K-fold Cross Validation R-Square
  • Example/Case Study
Register Now!
John Noguera
John Noguera

About John Noguera

John Noguera is Co-founder and Chief Technology Officer of SigmaXL, Inc., a leading provider of user-friendly Excel add-ins for Lean Six Sigma tools, statistical & graphical analysis and Monte Carlo simulation. He leads the development of SigmaXL and DiscoverSim with a passion for ease-of-use, practical & powerful features, and statistical accuracy. John is a certified Six Sigma master black belt and was an instructor at Motorola University. He has authored conference papers on Statistical Process Control and Six-Sigma Quality and is a contributing author in the Encyclopedia of Statistics in Quality and Reliability (Wiley).