Week 1: What is forecasting?

Week 1

Start with the forecasting mindset, the course toolkit, and the basic tsibble workflow used throughout the unit.

Prepare before class

Install or update R and RStudio, review the opening chapter of FPP3, and work through the tsibble introduction before class.

Seminar and workshop

Wednesday 04 March · Seminar 3:00pm to 3:50pm, workshop 4:00pm to 4:50pm · Building K Level 3, K321

Focus

• Forecasting as a statistical decision problem
• What makes a series easy or hard to forecast
• Using tsibbles and the course R workflow

Assessment

Next assessment: Week 2 quiz on Wednesday 11 March

Next assessment: Week 2 quiz on Wednesday 11 March

Workshop ActivitiesSlides PDFFPP3 Chapter 1Recordings

What you will learn this week

• How to think about forecasting from a statistical perspective
• What makes something easy or hard to forecast?
• Using the tsibble package in R

Pre-class activities

Before we start classes, make sure you are familiar with R, RStudio and the tidyverse packages. If you’ve already done one of ETX2250/ETC1010 or something equivalent you should be fairly familiar with these concepts and probably will not need much help. If you’re new to R and the tidyverse, then you will need to get yourself up-to-speed.

• Install/update R, RStudio. See https://otexts.com/fpp3/appendix-using-r.html
• Install required packages install.packages(c("tidyverse","fpp3", "GGally"), dependencies = TRUE)
• Explore StartR: https://startr.numbat.space/. Work through Getting started (5 modules) and Writing documents (1 module). Do as much of it as you think you need. For those students new to R, it is strongly recommended that you do all these. For those who have previously used R, concentrate on the parts where you feel you are weakest.
• Read Chapter 1 of the textbook and watch all embedded videos. Pay particular attention to Section 1.7.
• Read Section 2.1 of the textbook and watch the embedded video.

Slides for seminar

Download pdf

Seminar Code

week1-code.R

Tutorial exercises

NoteTutorial Learning Objectives

1. Work confidently with Quarto documents.
   • Open, run, and knit the IA_template.qmd file to PDF without errors.
2. Import and manage time series data in R.
   • Read CSV/Excel files, correctly set your working directory, and avoid file path errors.
3. Create and understand tsibbles.
   • Convert data frames to tsibbles using as_tsibble() and understand the time index and key variables.
4. Begin planning IA1.
   • Start thinking about your forecasting approach and discuss ideas with peers.

1. Walk through IA_template.qmd. Make sure you understand the quarto (qmd) file structure and make sure you can knit the file successfully to pdf format.
2. Discuss IA1 in class. How do you go about forecasting at the moment that you are untrained?
3. Complete Exercises 1, 3 and 5 from Section 2.10 of the textbook.

Your tutors will be in your tutorial class to assist you.

• Week 1 Tutorial Solution.html

Assignments

• IA1 is due on Friday 13 March.