Applied Time Series Analysis
ILRST 4550/ORIE 5550/STSCI 4550
Instructor: Maryclare Griffin
Teaching Assistant: Megan Gelsinger
Notes and Slides
Please keep in mind that these will be updated periodically as I catch and am otherwise made aware of typos.
Lecture Notes:
- Multivariate State-Space Models: See Chapter 6 of Shumway and Stoffer (2006) as well as Homes, Scheuerell, and Ward (2018).
- Multivariate AR/MA/ARMA: See Chapter 5, Section 7 of Shumway and Stoffer (2006) and/or Chapter 10 of Chan (2010).
- Basic Multivariate Time Series Concepts:
notes_12.pdf - Multivariate Regression:
notes_11.pdf - Stochastic Volatility Models:
notes_10.pdf - State-Space Models:
notes_9.pdf - ARFIMA:
notes_8.pdf- Coming soon, will not be tested or on homeworks. From last lecture before spring break.
- Non-Stationarity, ARIMA, ARCH/GARCH:
notes_7.pdf - Spectral Analysis/The Spectral Domain:
notes_6.pdf - Estimation and Model Selection:
notes_5.pdf - Forecasting:
notes_4.pdf - Autoregressive Moving Average (ARMA) Models:
notes_3.pdf - Basic time series concepts:
notes_2.pdf - Introduction and a review of linear regression:
notes_1.pdf
Lecture Code:
- More VAR/VMA/VARMA:
code_16.R - More Multivariate State-Space Models:
code_15.R - Multivariate State-Space Models:
code_14.R - VAR/VMA/VARMA:
code_13.R - More Vector Autoregressive Models:
code_12.R - Vector Autoregressive Models:
code_11.R - Stochastic Volatility Modeling:
code_10.R - More State-Space Modeling:
code_9.R - State-Space Modeling:
code_8.R - Fractional Differencing/ARFIMA:
code_7.R - ARCH/GARCH:
code_6.R - SARIMA:
code_5.R - More Spectral Analysis:
code_4.R - Motivating Spectral Analysis:
code_3.R - Estimation for ARMA:
code_2.R - Forecasting:
code_1.R
Exam Solutions:
Supplementary Lecture Material:
- An improved version of the figure I drew to explain model selection for AR(p)/MA(q) models:
model_select.pdf
Lab Materials:
- Materials for eleventh lab on Friday 4/26/19:
lab11 - Materials for tenth lab on Friday 4/19/19:
lab10 - Materials for ninth lab on Friday 4/12/19:
lab9 - Materials for eighth lab on Friday 3/22/19:
lab8 - Materials for seventh lab on Friday 3/15/19:
lab7 - Materials for sixth lab on Friday 3/8/19:
lab6 - Materials for fifth lab on Friday 3/1/19:
lab5 - Materials for fourth lab on Friday 2/15/19:
lab4 - Materials for third lab on Friday 2/8/19:
lab3 - Materials for second lab on Friday 2/1/19:
lab2 - Materials for first lab on Friday 1/25/19:
lab1
Lecture Slides:
- Homework 1 Review:
slides_3.html - Sample Autocorrelation Function:
slides_2.html - Linear regression slides:
slides_1.html
Time Series Textbooks (All Online, Free via Cornell Library):
- Shumway and Stoffer (2006) is our main reference. Based on my research, it’s the best regarded textbook for a course of this type. That said, there are some parts where notation gets quite confusing and we’ll stray from it a bit.
- Chan (2010) is a really lovely book that has very clear explanations, but sometimes goes a bit above and beyond the technical level we want for this class.
- Cowpertwait and Metcalfe (2009) is a simpler book that focuses more on
R. It’s not quite technical enough to be a primary reference for this course, but it is a very nice place to learn various concepts, e.g. how to simulate from different time series models. - Tsay (2010) is a on a similar but slightly more advanced level than our course, but it contains less
Rcode and is more financially oriented. - Brockwell and Davis (1991) is too technical for our purposes and doesn’t have much in the way of
Rexamples. But, it is very detailed and comprehensive. When I want to make sure I understand how something I’ll be teaching can be proven, I look here. - Homes, Scheuerell, and Ward (2018) is a very practically oriented online textbook motivated by time series problems in Fisheries and the Environmental Sciences.