Latest news
Welcome to the course.
The schedule for the course can be found via the link to webTimeEdit top of the page.

The course representatives for the course are: Caroline Almkvist (TKIEK), Kristoffer Andersson (MPNEM), Luqueri Gustafsson (GU), Linus Jonsson (TKIEK), Gustav Lindwall (MPNEM)

OBS: In the last week of teaching (week 20), lectures will be on Tuesday and Friday. The last exercise class is on Thursday in MVH12.

23/3: Project 1 is online.
24/3: If you missed the first lecture, make sure that you inform yourself about the "rules of the course" and talk to students that attended the lecture.
28/3: Fixed a typo in the project and added clarifications.
31/3: If you are not able to attend all lectures, you are responsible to get all relevant information and details that were discussed from somebody in class.
5/4: Some notes on the projects: 1) In Task 3, you are supposed to use the ACVF based on the data in x, i.e. the one you computed in Task 2. 2) If you have implemented the algorithms correctly, you only need to estimate the 6 coefficients needed for your prediction once in Task 4 and once in Task 5. 3) If you have implemented the algorithms correctly you should get the exact same (down to 4 decimal points at least) answer in terms of the estimated error and coefficients in Tasks 4 and 5.
7/4: Another note on the project: Note that the Durbin-Levinson algorithm in the lecture notes presupposes zero mean, so in Task 5 you have to include the a0 term as in Task 4.
21/4: Project 2 is online.
27/4: Project 1 is corrected and has been handed back in today's lecture. You can pick it up in the lecture tomorrow, Friday April 28, and the exercise class on Tuesday, May 2. Afterwards, it will be ready for pick up in front of Annika's office, where the handwritten solutions are handed in. Resubmission to pass (without bonus points) are due on May 28.
27/4: The instructions for Problem 3 d) in Project 2 has been updated.
2/5: Partial answer sheet updated. New version of the lecture notes uploaded with small changes for clarification.
5/5: The last exercise and the last lecture with Carl Lindberg as guest lecturer had to be switched (see below).
9/5: Note that you are meant to suppose that R is white noise in Tasks 5c-5e of Project 2.
10/5: The last exercise session (note: on Thursday the 18th of June) will be an all blackboard session with a repetition of the course content. Please send any suggestions on what exercises you want to be covered to Andreas!
15/5: The location of tomorrow's lecture has been changed to Pascal!
17/5: Note the change in office hours next week.
17/5: The final version of the lecture notes is online. The relation of SDE and time series analysis was cancelled due to the lack of math students in the lecture. Instead a review and overview on the course content was given.
18/5: Answer sheet updated. Project 2 has been corrected and is given back in the exercise session today, in the lecture tomorrow and after that outside of Annika's office.
22/5: After many requests, here is the re-exam from January 3, 2017, with its solution. However, we recommend that you spend the majority of your time on the exercises and not on this or the other exams. Note that many of the tasks and solutions of this and other exams are already in the lecture notes as examples, and are often explained in more detail there, so it is a good idea to focus on reading and understanding the lecture notes rather than study the model solutions of the exams.
30/5: Don't forget to bring a calculator to the exam! Also, if you are looking at the old exams, note that there is an assumption missing in the 15/16 exam, see below.
21/6: The exam is marked and you can find your result here if you remember you code. The results should also be visible in Ladok within the next days. Recall that you need 30 points (with bonus) to pass (GU: 30 for G, 45 for VG; Chalmers: 30 for 3, 40 for 4, 50 for 5). The solution to the exam will be available within the next days.
22/6: The solution to the exam is online. The results are also now finalized in Ladok.
22/6: The re-exam is planned on Tuesday, August 15 in the afternoon.
21/8: The first re-exam is marked and you can find your result here if you remember you code. The results will be put into Ladok as soon as possible. Please be patient. Recall that you need 30 points (with bonus) to pass (GU: 30 for G, 45 for VG; Chalmers: 30 for 3, 40 for 4, 50 for 5).
25/8: Notice that from now on, it is no longer possible for Chalmers students to take an exam without being registered (even if space in the exam room allows). Be aware of this in case you plan to take the second re-exam in the course.
Teachers
Course coordinator: Annika Lang
Email: annika.lang@chalmers.se
Office: MVL2086
Office hour: Thursdays 11.00-12.00 (no office hour April 13, on April 20: 10.00-11.00)

Teaching assistant: Andreas Petersson
Email: andreas.petersson@chalmers.se
Office: MVL3048
Office hour: Tuesdays 08.30-09.30 (except for week 16 and 21, when it's Wednesday 08.30-09.30)
Course literature
Main literature:

Additional texts:

Additionally lecture notes will be provided in parallel. (Final version: May 30)

You might also be interested in:
Programme


Lectures
Week Chapter
Contents
12(1)

Introduction to time series and stationarity, "rules of the course"
12(2)
[BD] 2.1, 2.4 Characterization of stationarity
13(1)
[BD] 2.5 Forecasting stationary time series
13(2)
[BD] 2.5 Forecasting stationary time series
14(1)
[BD] 1.5
Trend and seasonality
14(2)
[BD] 2.2, 3.1
Linear processes, ARMA (definition, existence, uniqueness, causal, invertible)
17(1)
[BD] 3.2, 5.1
ARMA (ACVF, PACF, parameter estimation)
17(2)
[BD] 5.1, 5.5, 3.3, 5.4
Parameter estimation with MLE, order selection, forecasting, ARIMA
18(1)
[BD] 6 [T] 3 ARIMA, ARCH
18(2)
[T] 3
GARCH, introduction to nonlinear models
19(1)
[T] 4.1
Examples of nonlinear models, nonparametric methods
19(2)
[T] 4.2, 4.4
Nonlinearity tests, forecasting nonlinear models
20(1) (Tue)
[T] 4.4
Forecasting nonlinear models, relating SDEs and time series models (in Pascal!)
20(2) (Fri)

Financial time series in practice (Carl Lindberg)



Exercise classes
Exercises to prepare for the exercise class
Week Exercises
13
[BD] 1.1, 1.3, 1.4, 1.6, 1.7 and exercises in basic probability, at least 1-4
14
Example 2.3.8 from the lecture notes. Exercise 6 from the updated probability exercises.
[BD] 2.1, 2.2, 2.3, 2.4, 2.7, 2.8, 2.14ab, 2.15*, 2.20, 2.21abcd
17
[BD] 1.10, 1.11, 1.15, 3.1abcde, 3.3abcde, 3.6, 3.7, 3.8
18
[BD] 3.4, 3.11, 5.3, 5.4abde**, 5.8, 5.11, 5.12
19
[BD] 6.1 and additional ARCH and GARCH exercises.*** Exercise 2 will be covered on the blackboard.
20 (Thur)
2 non-linear model exercises and repetition .

* Replace the condition "n > p" with "n >= p".
** You may (and should) assume that the AR(2) model is causal.
*** The formula for a geometric sum and series is useful here.
Start with the black exercises and do the harder red ones when you have time.
Note that exercises marked in bold are discussed on the blackboard in the exercise session.
There is now a partial answer sheet available.
Course requirements
Basic knowledge in probability theory and mathematical statistics. The assumed background is summarized in Chapter 1 of the lecture notes. Each student is responsible to make sure that he/she is familiar with this content.
Projects
Two projects have to be passed.
Project 1: deadline for bonus points: 23/4, data: gaussian.mat
Project 2: deadline for bonus points: 14/5, data: dow_jones.mat
global deadline for both projects (no bonus points possible): 28/5

Do not forget to read the project instructions carefully!
Examination
To pass the course two projects (each 2.5 hp) have to be handed in and passed in groups of up to two students. These are graded with pass (G) and fail (U). Furthermore a written exam (2.5 hp) has to be passed with at least 50% of the overall points which is graded with VG/G/U for GU students and 5, 4, 3, U for Chalmers students. The overall grade of the course is determined by the exam but to pass the course with 7.5 hp all three components have to be passed. Solutions and reports for home assignments should be sent as written on the problem sheet. Solutions or reports sent later than the deadlines will not be graded and are "failed". Each student is responsible on his/her own that his/her own theoretical homework is submitted before the deadline. For the exam you are allowed to bring four pages (two sheets) of your own handwritten notes and a simple calculator (which will not be necessary to solve the exam). You will be able to get up to 4 bonus points per project for good solutions which are valid at the (first) ordinary exam.
Examination procedures
In Chalmers Student Portal you can read about when exams are given and what rules apply on exams at Chalmers.
At the link Schedule you can find when exams are given for courses at University of Gothenburg.
At the exam, you should be able to show valid identification.
Before the exam, it is important that you report that you want to take the examination. If you study at Chalmers, you will do this by the Chalmers Student Portal, and if you study at University of Gothenburg, so sign up via GU's Student Portal.

You can see your results in Ladok by logging on to the Student portal.

At the annual examination:
When it is practical a separate review is arranged. The date of the review will be announced here on the course website. Anyone who can not participate in the review may thereafter retrieve and review their exam on Mathematical sciences Student Office, open hours. Check that you have the right grades and score. Any complaints about the marking must be submitted in writing at the office, where there is a form to fill out.

At re-examination:
Exams are reviewed and picked up at the Mathematical sciences Student Office, open hours. Any complaints about the marking must be submitted in writing at the office, where there is a form to fill out.
Old exams
Exam 2014/15 (first year with a written exam) and its solution
Exam 2015/16 and its solution. N.B.: In Problem 1, the assumption that Cov(X_s,Z_t) = 0 for all time points s < t is missing.
Exam 2016/17 and its solution