Course PM

This page contains the program of the course: lectures, exercise sessions and project. Other information, such as learning outcomes, teachers, literature, old exams and examination, are in a separate course PM.

Program

All lectures and exercise sessions will be on campus only!

The following program is preliminary and is regularly updated. Check the course home page often!

Lectures

Lectures will take place on campus on Tuesday, 10.00-11.45, in MVF31 and Thursday, 13.15-15.00, in Pascal. The detailed schedule can be found in TimeEdit. 

 

Day	Sections	Lecture notes
25/3		Introduction to the course Introduction to time series [LP] 2.1
27/3	[BD] 2.1	Stationary time series, autocorrelation function, statistical quantities [LP] 2.2-2.3
1/4	[BD] 1.6, 2.4, 2.5	Statistical quantities, tests for iid, introduction to forecasting, best preditors [LP] 2.3-2.4
3/4	[BD] 2.5	Best linear predictors, Durbin-Levinson algorithm, lemma innovations algorithm [LP] 2.4
8/4	[BD] 2.5, 1.5, 6.4	Innovations algorithm, trend and seasonality [LP] 2.4-2.5
10/4	[BD] 2.2, 3.1	Linear time series, ARMA models [LP] 3.1-3.2
24/4	[BD] 3.2, 5.3-5.5	ARMA models: (P)ACF, parameter estimation, order identification [LP] 3.2.1-3.2.4
29/4	[BD] 3.3, 6.1-6.4	ARMA models: forecasting, (S)ARIMA and unit root tests [LP] 3.2.5-3.3
6/5	[BD] 7.1-7.2, [T] 3	Introduction to GARCH models [LP] 4-4.1
8/5	[BD] 7.1-7.3 [T] 3	Parameter estimation, order selection and extension of GARCH models [LP] 4.2-4.4
13/5	[T] 4.1 [BD] 11.3	GARCH in practice, nonlinear models [LP] 5.1
15/5	[T] 4.1, 4.2 [BD] 11.3	Testing for nonlinearities, nonparametric methods [LP] 5.2-5.3
20/5	[T] 4.4	Bootstrapping, forecasting, and error measures [LP] 5.4
22/5		Slot for asking questions (no lecture)
27/5		Slot for asking questions (no lecture)

 

Recommended exercises

The exercise sessions are on Fridays 8:00-11:45 in MVF31.

 

Day	Exercises
28/3	[BD] 1.1, 1.3*, 1.4, 1.6, 1.7    Extra exercises in basic probability (1, 3, 6 and 9 will be covered)
4/4	[BD] 2.1, 2.2, 2.3, 2.4, 2.7, 2.8, 2.14ab, 2.15, 2.20, 2.21
11/4	[BD] 1.10, 1.11, 1.12a, 1.13, 1.15, 3.1abcde, 3.3abcde, 3.6, 3.7, 3.8.
25/4	[BD] 3.4, 3.11, 5.3, 5.4abde, 5.8, 5.11, 5.12.
9/5	[BD]  6.1, 1.8  and  additional ARCH and GARCH exercises (2, 4, and 6 will be covered).
16/5	[BD] 11.3 and Non-linear model exercises .
23/5	Project presentations.

  You are expected to try to solve the exercises on your own before the solutions are presented in the exercise sessions. See also the partial answer sheet .

* You may assume that the process has densities associated with its finite dimensional distributions.

Project

In addition to the written exam, the project is another way to earn important and grade-determining points for the course. It is not a mandatory component, but participation is strongly recommended. Financial time series is first and foremost a practical subject, and the purpose of the project is to highlight this particular aspect.

The problems to be solved are taken from real-life situations where they have been used as a take-home assignment for junior quantitative analyst positions at a well-established quantitative hedge fund. The project runs throughout the entire study period, starting in the first study week, and you will work in groups together with other students.

The problems are in no way meant to be tied to the theory covered in lectures, although certain concepts may certainly prove useful. However, the idea is not to "wait for" the relevant theory to be covered in a lecture but rather to tackle the assignment as one would in the professional world. Your boss simply does not care which courses you have taken at university. He or she wants concrete and practical solutions to real-world problems. The less advanced and transparent the better!

You are free to use any books, chatbots, software, etc., that you find suitable. What's important is to find reasonable and robust solutions that you can personally justify. The projects will be presented in two different ways. A written report will be required, and some groups (most of them) will also need to present a randomly selected sub-task to the rest of the class.

Material

Project statement: project_statement

Data: spiff_data.csv

Guidelines for the report

The report should be organised into subproblems, as the project itself. For each problem, state the task you are going to solve using your own words. Then describe how you solved the task and, if possible, what resources you have used (literature, lecture notes, articles). You should explain your understanding of the problem and your theoretical strategy on how to solve it when relevant. The implementation should also be described in your own words. This can include, for example, mentioning what MATLAB/Python functions/libs you used for solving the task. After this, state the result by giving resulting numbers, plots etc. Comment on your results, interpret and discuss if they are as you expected. Why or why not?

If you struggle with MATLAB/Python, make sure to first of all consult the documentation. For instance, if you want to find out how to calculate an autocorrelation in MATLAB/Python,  google it first. Make sure you read documentations of every function you use so you understand what it does.

If you have not used LaTeX before, the easiest way to get started is to register for an account at  Overleaf, which is an online editor. Chalmers students can use their @student.chalmers.se email address in the registration in order to automatically get a premium account. For an introduction to LaTeX, see  Getting Started with LaTeX  for a guide in English or  LaTeX-tips  by Niklas Andersson and Malin Palö for a guide in Swedish.

Points

The project is divided into 4 subproblems and each of them can give no more than 2 points. The same goes for the written report which also can give a maximum amount of 2 points. Thus, the whole project can reward each member of the group a total of 0-10 points.

Deadlines

Report: Should be handed in by email no later than Sunday 2025-05-18 at 23:59.

Presentations: Takes place 08:15-11:45 on Friday 2025-05-23.

 

Examination

The final grade is derived from the total points collected during the course. Points can be earned in two different ways:

Project: max 10 points

Written exam: max 15 points

The grading matrix for Chalmers/GU is the following:

Chalmers: grade 3 >= 11 points, grade 4 >= 16 points, grade 5 >= 20 points.

GU: grade G >= 11 points, grade VG >= 18 points.

 

Note that the only possible way to earn grades 4, 5, VG is to work on the project.