Week 11: Dynamic regression

What you will learn this week

  • How to combine regression models with ARIMA models to form dynamic regression models
  • Dynamic harmonic regression to handle complex seasonality
  • Lagged predictors

Pre-class activities

Read Chapter 10 of the textbook and watch all embedded videos

Slides for seminar

Download pdf

Workshop activities

Seminar Code

Tutorial exercises

NoteTutorial Learning Objectives
  1. Fit dynamic regression with ARIMA().
    • Able to specify and fit a regression model with ARIMA errors
    • Able to assess model fit using standard regression diagnostics and ARIMA residual diagnostics; and to use the fitted model to forecast when future predictor values are known.
  2. Evaluate and interpret dynamic regression.
    • Able to compare competing specifications using standard criteria;
    • Able to interpret output from joint regression-and-error models
    • Able to discuss strengths and limitations of the forecasts and the prediction intervals.

Assignments

  • GA4 is due on Tuesday 26 May.

Weekly quiz