Introduction to Time Series: Fall 2023

Stat 153

Instructor: Ryan Tibshirani (ryantibs at berkeley dot edu)
GSI: Alice Cima (alice_cima at berkeley dot edu)
Reader: David Zhang (dzhang2324 at berkeley dot edu)

Please email the GSI with any issues; the Instructor will be looped in only as-needed.

Class times: Mon, Weds, Fri, 1-2pm, SSB 20
Lab times: Fri, 2-4p and 4-6pm, Evans 332
Office hours: RT: Mon, 2-3pm, Evans 417

Handy links:
• Syllabus
• GitHub repo (source files for lectures and homeworks)
• Ed discussion (for class discussions and announcements)
• bCourses (for grade-keeping and homework solutions)
Go to:   Schedule | Homework | Supplementary resources

Schedule

Here is the estimated class schedule. It is subject to change, depending on time and class interests.

Week 1: Aug 23 - Aug 25 Characteristics of time series pdf, html, source
Week 2: Aug 28 - Sep 1 Measures of dependence pdf, html, source
Week 3: Sep 6 - Sep 8 Regression and prediction pdf, html, source Hw 1 due Thur Sep 7
Week 4: Sep 11 - Sep 15 Regression and prediction "
Week 5: Sep 18 - Sep 22 Regularization and smoothing pdf, html, source Hw 2 due Thur Sep 21
Week 6: Sep 25 - Sep 29 Regularization and smoothing "
Week 7: Oct 2 - Oct 6 Spectral analysis pdf, html, source Hw 3 due Fri Oct 6
Week 8: Oct 9 - Oct 13 Spectral analysis "
Week 9: Oct 16 - Oct 20 ARIMA models pdf, html, source Midterm Fri Oct 20
Week 10: Oct 23 - Oct 27 ARIMA models "
Week 11: Oct 30 - Nov 3 ARIMA models "
Week 12: Nov 6 - Nov 8 ETS models pdf, html, source Hw 4 due Mon Nov 6
Week 13: Nov 13 - Nov 17 ETS models "
Week 14: Nov 20 [Nothing! Enjoy Thanksgiving]
Week 15: Nov 27 - Dec 1 Advanced topics pdf, html, source Hw 5 due Fri Dec 1,
Final Weds Dec 13

Homework

Supplementary resources

We will (roughly) follow some chapters of the following two books, which you can look at as supplements to the lecture notes. The first should be available to you by searching for it online through the UC Berkeley Library, and the second is freely available at the link below. Below are two other references on time series that may be helpful as well. The first is more advanced, and the second more elementary.