Statistics 520

Time Series and Applications

Spring 2024

The final will be on Tuesday, Apr 30, 3:30-5:30pm, in SCHM 113. You can bring 4 letter-size, double-sided crib sheets, and a calculator; no mobile devices. Here is an old final.

Course outline

This course offers an introduction to the analysis of time series. Topics to be covered include the autocorrelation and spectrum of stationary processes, the structure, estimation, and identification of AutoRegressive (Iterated) Moving Average (ARIMA) models, forecasting, model diagnostics, seasonal models, and transfer function models. Software tools will be an important part of the course, for which we will mainly draw on the resources available in R, an open-source programming environment for data analysis and graphics.

Prerequisite

Basic concepts of probability theory, working knowledge of statistical inference, linear models, and matrix algebra.

Textbook

• Time Series Analysis: Forecasting and Control, by Box, Jenkins, and Reinsel.
  The data sets used in the text are given here.

References

• Time Series: Theory and Methods, by Brockwell and Davis.
• Spectral Analysis and Time Series, by Priestley.
• An Introduction to R, by the R Development Core Team.
• Using R for Data Analysis and Graphics - An Introduction, by Maindonald.
• Modern Applied Statistics with S-Plus, by Venables & Ripley.

Software

We will be using R, an open-source programming environment for data analysis and graphics, as the primary platform for computation and graphics. R resources are to be found at The Comprehensive R Archive Network.

Course Work

There will be about 7--8 assignments, with "written" and "lab" problems mixed in. There will also be a midterm and a final. The midterm and the final are closed-book, but you are allowed 4 pages of letter-size double-sided crib sheets.

Grading

The letter grade will be based on assignments (40%), midterm (30%), and the final (30%).

Lecture Notes

Assignments