Forecasting Essentials and Notes: Online Resource

Introduction

Hello! I’m Jonathan, and I want to teach you time series analysis I have designed this website to accompany the University of Chicago course ADSP 31006 “Time Series Analysis and Forecasting”. Although the course will mostly be taught in a traditional lecture format, I would like to use this website to provide backing material for the lectures.

Recommended textbooks

Unlike my statistics course website, I do not intend that this course website be considered the principle text for the class. We will have two primary textbooks (described below), and the notes in these pages supplement the readings without replacing the readings.

  • Forecasting: Principles and Practice 3rd edition, by Rob Hyndman and George Athanasopoulos

    This book is freely available and one of our two major reference sources. The book relies heavily on R code using the tidyverse constellation of packages and the new fable package written by the authors, which interleaves specifically with the tsibble package. Readers who prefer base R may instead read the book’s second edition (also freely available), and readers who prefer Python will benefit from the new Python edition (also freely available).

  • Practical Time Series Analysis, by Aileen Nielsen

    This is the second of our two major reference sources. In contrast to the Hyndman and Athanasopoulos textbook, Nielsen includes more on-the-job tips about working with real datasets, structuring and storing the data, and putting forecasting models into production. She uses a combination of R (using the less-common data.table environment) and Python examples, and describes time series analysis from both a statistical and a machine learning perspective.

  • Time Series Analysis: Forecasting and Control 5th edition, by George Box, et al.

    One of the classic texts in the field. Box and his co-authors have introduced and refined (over several decades) the best all-purpose textbook from a purely statistical perspective. They spend less time discussing programming considerations or machine learning models.

How these notes were made

I assembled these notes using Quarto, a publishing system built around the Pandoc markdown language. I wrote all the code backing these notes in R, and alongside every figure or table you can find the corresponding R code.

Neither the text nor the R code in these notes were generated by AI tools: for better and worse the opinions expressed here are my own, and the I’ve described these concepts in my own voice.1 Complaints can be submitted here.

  1. AI assistance was used to brainstorm case studies and examples, and to help with the layout and coding of the website itself.↩︎