Syllabus

Lectures TR 1000-1120 GLSN 100
Instructor: Charlotte Wickham, 255 Weniger
charlotte.wickham@stat.oregonstate.edu
Office hours: Mon & Weds 1-2pm Weniger 255
TA: Chris Comiskey comiskec@onid.oregonstate.edu

Course Content

The analysis of serially correlated data in both time and frequency domains. Autocorrelation and partial autocorrelation functions, autoregressive integrated moving average models, model building, forecasting; filtering, smoothing, spectral analysis, frequency response studies.

Topics covered will include:

• Exploratory analysis and graphical display of time series
• Common stationary models for time series and their estimation
• Forecasting of time series
• Regression with errors described by a time series model
• Analysis of time series in the spectral domain

Student Learning Outcomes

After completing ST565 you will be familiar with the issues in understanding, analyzing and interpreting data measured in time. You will be able to:

• Explore and graphically summarise trend, seasonality, correlation and variation in time series data using R.
• Define the concept of stationarity and describe it’s importance in time series analysis.
• Define basic stationary time series models: white noise, AR(1) and MA(1).
• Define the autocovariance and autocorrelation functions and derive the autocorrelation function for basic time series models.
• Apply the Box-Jenkins modelling approach to identify, fit, check and forecast SARIMA models for time series data.
• Estimate and interpret regression models with time series structure on the errors.
• Define the spectrum and interpret a periodogram of a time series.

Tentative Schedule

Tentative Schedule

Evaluation of Student Performance

40% homework + 20% midterm + 20% project + 20% final

Homeworks

Roughly weekly homeworks may consist of readings, mathematical derivations, simulations and complete data analyses. Homeworks will be made available on the class website and, unless specified otherwise, handed in at the start of class on Tuesday. Late homeworks will not be accepted. Your lowest homework score will be dropped.

Midterm

Tentatively scheduled for Thrusday of week 6.

Project

Proposal due week 7, final project due week 10… more details closer to the time.

Learning Resources

This quarter I am planning to follow quite closely: The Analysis of Time Series: An Introduction, Sixth Edition (Chapman & Hall/CRC Texts in Statistical Science)

This is available to read online through the OSU library. If you want to buy a reference book for time series this is a good one to start with. The only downside is it has very little code for getting things done in R (I will generally provide this in the lecture notes). It is not required that you buy this book, but I do recommend supplementing the lecture material with the readings provided from this book, or use one of the other freely available books below.

For Stats students: there is also a copy available in the Stats Department Library.

Optional Three other books I have found useful and are available online:

• Time Series Analysis and Its Applications: with R Examples by Robert Shumway and David Stoffer. This is quite a theory heavy book. Probably only suited to people with a strong Math Stat background. If you want to know the why of a particular result, this is the place to look first.
• Introductory Time Series with R, P Cowperwait & A Metcalfe. This is a much more applied (i.e. less math) book. Great if you just want some intuition and how to do things in R without the theory.
• Time Series Analysis With Applications in R, Jonathan D. Cryer and Kung-Sik Chan. Somewhere between the previous two books. A slightly different approach.

Web site

Course materials (lecture notes and homeworks) will be posted at stat565.cwick.co.nz. Class email announcements and grades will be distributed through canvas.

Disability statement

Accommodations are collaborative efforts between students, faculty and Disability Access Services (DAS). Students with accommodations approved through DAS are responsible for contacting me prior to or during the first week of the term to discuss accommodations. Students who believe they are eligible for accommodations but who have not yet obtained approval through DAS should contact DAS immediately at (541) 737-4098.

Academic integrity

Academic dishonesty is a serious offense and will be addressed following the guidelines set out in the Academic Regulations of OSU (go to http://catalog.oregonstate.edu, click on Registration Information → Academic Regulations, and read AR 15).

The Student Conduct Code http://studentlife.oregonstate.edu/studentconduct/offenses-0 defines Academic dishonesty as

… an act of deception in which a Student seeks to claim credit for the work or effort of another person, or uses unauthorized materials or fabricated information in any academic work or research, either through the Student’s own efforts or the efforts of another.

Examples include, but are not limited to, the following:

• verbatim copying of another student’s homework assignment
• copying off another student’s exam
• using prohibited materials (e.g., cell phone, cheat sheet) during an exam
• communicating with another student during an exam
• changing answers on an exam after the exam has been graded
• unattributed use of material copied from an article, textbook, or web site
• continuing to write on an exam after the instructor or TA has asked for the exams to be handed in.