Week 3: Time series decomposition
Week 3
Break time series into interpretable components so trend, seasonality, and remainder can be analysed separately.
Quiz highlight
Week 3 quiz
Due Wednesday 18 March
Quiz links switch with your selected course, so this stays as the main weekly action.
Prepare before class
Read Chapter 3 of FPP3 and come in ready to distinguish trend-cycle, seasonal, and remainder components.
Seminar and workshop
Wednesday 18 March · Seminar 3:00pm to 3:50pm, workshop 4:00pm to 4:50pm · Building K Level 3, K321
Focus
- Transformations that stabilise variation
- Decomposition into trend-cycle, seasonal, and remainder parts
- Seasonal adjustment
Assessment
Week 3 quiz on Wednesday 18 March
Week 3 quiz on Wednesday 18 March
What you will learn this week
- Transforming data to remove some sources of variation
- Decomposing a time series into trend-cycle, seasonal and remainder components
- Seasonal adjustment
Pre-class activities
Read Chapter 3 of the textbook and watch all embedded videos
Slides for seminar
Seminar Code
Tutorial exercises
NoteTutorial Learning Objectives
- Visualise and assess time series transformations.
- Create appropriate graphs for multiple time series and apply transformations when needed.
- Evaluate the usefulness Box–Cox transformations.
- Able to explain when and why a Box–Cox transformation is or is not helpful for a given dataset.
- Apply time series decomposition techniques.
- Able to decompose a time series into trend, seasonal, and remainder components using STL decomposition and interpret the results.
Complete Exercise 2, 3, 10 from Section 3.7 of the book.
Assignments
Weekly quiz
- Week 3 quiz: Open ETF3231 quiz Open ETF5231 quiz — Due Wednesday 18 March.