STAT 5379 -- Time Series Analysis -- Spring 2023
Instructor
Dr. Alex
Trindade, 228 Mathematics & Statistics Building.
E-mail: alex.trindade"at"ttu.edu.
Course Meets: TR 14:00 - 15:50 in MATH 110.
Office Hours: ???, .
Text Books
Required:
- Time Series Analysis and its Applications: With R Examples,
Shumway & Stoffer, 4th edition (2017), Springer. [Denoted by S&S.]
- Introduction to Time Series and Forecasting, Brockwell and Davis, 3rd edition (2016), Springer. [Denoted by B&D.]
Helpful:
- Time Series Analysis, Wilfredo
Palma, (2016), Wiley. (Similar coverage.)
- Applied Time Series Analysis, Woodward, Gray & Elliott, (2012), CRC Press. (Similar coverage.)
- Time Series Analysis: With Applications in R , Cryer & Chan, 2nd edition (2008), Springer. (Similar coverage.)
- Forecasting: principles and practice, Hyndman & Athanasopoulos (2013), OTexts. (Updated coverage of forecasting methods.)
- Time Series: Theory and Methods, Brockwell and
Davis, 2nd edition (1991), Springer. (More rigorous than their "Intro" book.)
Course Notes
I intend to closely adhere to these notes which were transcribed by a student in the spring 2019 class.
Course Objectives and Syllabus
The course is aimed at providing a solid introduction
to the methods and underlying theory of modern time series analysis. The main
focus will be on modeling and forecasting second order stationary
processes with ARMA models. The latter part of
the course aims to cover more advanced/specialized topics like spectral analysis, state-space models, and nonlinear models. Applications will involve the use of R. The prerequisite for the
course is the graduate level mathematical statistics sequence STAT 5328-5329. Chapters to be covered are as follows (S&S):
- Chapt 1: Characteristics of Time Series.
- Chapt 2: Time Series Regression and Exploratory Data Analysis.
- Chapt 3: ARIMA Models.
- Chapt 4: Spectral Analysis.
- Chapt 5: Specialized Topics: long-memory, unit-roots, lagged regression and nonlinear models.
- Chapt 6: State-Space Models.
Expected Student Learning Outcomes
The heart of the course will consist of chapters 1-3 of the text, concentrating on the following
major topics: Stationary processes; autocorrelation; ARIMA models; model-based inference; prediction. By the end of the course the student should have a good grasp of concepts, theory
and methodology pertaining to the analysis of time series data: accounting for trend & seasonality; assessing the presence of autocorrelation; ARIMA model fitting; regression models with ARMA noise; model-based inference & prediction.
Methods of Assessing the Expected Learning Outcomes
The expected learning outcomes for the course will be assessed through a mix of homework assignments and tests. The course grade will
be determined from homework problem sets (20%), two midterm tests (25% each), and a comprehensive final
exam (30%). The traditional grading scale will be used:
- A: 90-100%.
- B: 80-89%.
- C: 70-79%.
- D: 60-69%.
- F: 0-59%.
The test schedule is as follows:
- Test 1: Feb 23 (after Hwk 5).
- Test 2: Apr 6 (after Hwk 9).
- Final Exam: Takehome.
Homework Problem Sets
There will be weekly problem sets from the text due on thursdays. All work is to be uploaded to Blackboard. No late submissions will be accepted. Only a subset of the hwk may be graded; if your hwk omits the problem(s) chosen to be graded your grade will be zero. Start each problem on a new page.
- Set 0 (due Jan 14): B&D Problems 1.1.
- Set 1 (due Jan 21): B&D Problems 1.4; 1.7. S&S Problems 1.2; 1.5.
Software
We will use R as the primary software tool. Some problems and assignments will require extensive use of computing. While we will focus on the theory, the applied computing aspect is an important complement that greatly helps in understanding the methodology. For details on R see my statistical computing page, and especially the section on "time series".
Policies
- What to do in case of an emergency. If a student encounters a personal problem that affects their ability to attend class or complete their work on time, they should first consult their instructor. In exceptional circumstances, students may be directed to the Dean of Students office, phone (806-742-2984), email (deanofstudents@ttu.edu). The Dean of Students can help with emergencies including COVID, car accidents, death of a family member, inability to afford food, health issues, and more. (In exceptional circumstances, the Dean of Students can authorize exceptions to class policies.) In addition, Title IX reporting and support resources are available here.
- Class Attendance. Your attendance alone will not impact your grade,
but missing exams and assignments will.
- Make-up Exams: These may be granted in exceptional circumstances after you have followed the above protocol on What to do in case of emergency.
- Absence for observance of a religious holy day: See this
link.
- Absence due to officially approved trips: The Texas Tech University Catalog states that the department chairpersons, directors, or others responsible for a student representing the university on officially approved trips should notify the student's instructors of the departure and return schedules in advance of the trip. The instructor so notified must not penalize the student, although the student is responsible for material missed. Students absent because of university business must be given the same privileges as other students.
- ADA accommodations, Academic Integrity, COVID-19. See this
link.
- Civility in the Classroom. It is expected that everyone will behave
in a manner that is conducive to learning. One common disruption is cell
phones. Please turn these off in class.
- Electronic Devices in Tests. In the spirit of keeping costs down, I will permit the usage of apps on smart devices (phones, tablets, laptops, etc.), but any kind of communication or accessing of the web via these devices is forbidden.
- Collaboration. My policies on this are as follows.
- Homeworks: Discussion with peers regarding material/concepts covered in the
course is permitted, and is encouraged since it usually leads to greater comprehension. However, each person must write up his/her own
solution to a particular problem, and not simply have someone else do it for them.
- Tests: Any form of collaboration on tests, including e-device communication or trying to see what the person next to you is writing, is strictly forbidden and will not be tolerated.
top of page