Lesson 10: Regression Pitfalls

Overview of this Lesson

In this lesson we'll look at some of the main things that can go wrong with a multiple linear regression model. We'll also consider methods for overcoming some of these pitfalls. In particular, we'll cover:

  • Nonconstant variance and weighted least squares
  • Autocorrelation and time series methods
  • Multicollinearity, which exists when two or more of the predictors in a regression model are moderately or highly correlated with one another.
  • Overfitting
  • Excluding important predictor variables
  • Extrapolation
  • Missing data
  • Power and sample size
Key Learning Goals for this Lesson:
  • Know the main issues surrounding nonconstant variance.
  • Use weighted least squares to mitigate some nonconstant variance problems.
  • Know the main issues surrounding autocorrelation.
  • Use time series methods to mitigate autocorrelation problems.
  • Know what multicollinearity means.
  • Distinguish between structural multicollinearity and data-based multicollinearity.
  • Understand the effects of uncorrelated predictors on various aspects of regression analyses.
  • Understand the effects of multicollinearity on various aspects of regression analyses.
  • Understand variance inflation factors and how to use them to help detect multicollinearity.
  • Know the two ways of reducing data-based multicollinearity.
  • Understand how centering the predictors in a polynomial regression model helps to reduce structural multicollinearity.
  • Know the main issues surrounding other regression pitfalls, including overfitting, excluding important predictor variables, extrapolation, missing data, and power and sample size.