Week 10: Multiple regression and forecasting

What you will learn this week

  • Useful predictors for time series forecasting using regression
  • Selecting predictors
  • Ex ante and ex post forecasting

Pre-class activities

Read Chapter 7 of the textbook and watch all embedded videos

Exercises (on your own or in tutorial)

Complete Exercises 11-16 from Section 9.11 of the book.

Solutions to Exercises

Slides for seminar

Download pdf

Seminar activities

  1. Fit a regression model with a piecewise linear trend with Fourier terms for the US leisure employment data.

    leisure <- us_employment |>
        Title == "Leisure and Hospitality",
        year(Month) > 2001
      ) |>
      mutate(Employed = Employed / 1000) |>
      select(Month, Employed)
  2. Does the model fit well? What are the implications for forecasting?

  3. Produce forecasts of US leisure employment using your best regression model.

  4. Why don’t you need to forecast the predictors?

R code used in seminar