5. Linear Regression: Part I


  • Linear regression refresher 
  • Regression for forecasting vs. inference 
  • Linear, exponential, polynomial trends 
  • Additive and multiplicative seasonality 
  • De-trending and seasonal adjustment 
  • Using the model for generating forecasts 
  • Measuring predictive accuracy 
  • Global vs. local patterns 
  • Irregular patterns



Please read: 
Chapter 5 (without Section 5.5)

Assignment: Capturing trend and seasonality with regression

Chapter 5: Problem 1

Chapter 9.1 
  • How can a regression model be fitted to the demand series, given the inter-day and intra-day cycles? Mention the response (Y) and predictor variables (X’s) in your suggested regression model. 
Chapter 5: Problem 4 (requires AR material)

In this assignment, you will investigate the effect of an event on a time series by generating pre-event forecasts using linear regression. 

You will use linear regression to capture patterns such as trend and seasonality, and gain experience using XLMiner for generating regression-based forecasts.

Download September 11 Travels from ForecastingBook.com/datasets