Statistics for financial times series



Statistics is the science of uncertainty and variation. This course is about the statistics of time series used economic and finance problems. The aim of this course is to teach students to apply times series financial econometrics techniques sensibly in the context of real-world empirical problems. Using R and Rstudio Studio Server Pro, students will be taught statistical techniques which underpin quantitative investigation in the finance.

Learning outcomes

  1. Begin to understand econometrics as a science of uncertainty and variation.
  2. Introduction to the ethical application of econometrics.
  3. Exhibit intellectual humility and discipline in data analytics.
  4. Understand the iterative process of real-world data analysis.
  5. Understand how to use statistical techniques to calibrate answers to many problems posed in Finance.
  6. Understand how to source, prepared and encode financial time series data.
  7. Obtain analytical skills to identify patterns in data.
  8. Understand how to robustly infer real world effects from statistical analysis.
  9. Understand how to encode analytical questions using statistical software.
  10. Work independently to towards an empirical goal.

Professional skills

  1. Introduction to the “tidy” data principles of Hadley Wickham in RStudio.
  2. Introduction to “tidyverse” programming style guide.
  3. Introduction to cloud computing using RStudio Server Pro.
  4. To interpret the results of robust statistical analysis of financial data sensibly.
  5. Principles of appropriate data visualisation.
  6. Introductory software skills in visualisation and statistical analysis of financial data.
  7. The ability to work independently to glean meaning from noisy financial data.
  8. Advanced professionalism through improved independent learning/research techniques.


To pass this module students must obtain an overall mark of 50%. Students DO NOT have to pass each individual element to pass the module. The assessment is broken down as followings:

Prediction project (50%)

Students are asked to deliver an individual empirical assignment. Students should use an RMarkdown report to produce an HTML or pdf project report. Due end of week 5 submitted electronically via TurnitinUK. The lecturer revise the right to orally exam students after each assessment if he suspects foul-play.

End of Term Class Assessment (50%)

There will be practical timed assessment at the end of the course based on all the material up to that point. This will be run on the QMS Remote Analytics platform. The assesssment is be a mix of theoretical, computational and interpretative. Some questions will be based on students’ ability to analyse some financial data which will be provided. All assessments are based on material discussed in lectures, workshops and the directed independent learning.

Assessment protocols and learning tips

In both cases, it is important to learn how to read and critique academic papers. This is a learning process which requires practice. This link provide an excellent guide.

How to get a top grade

I am passionate about student development. I use the latest knowledge transfer science to activate permanent changes in students' understanding. I achieve this through learning by growth rather than memory. This is especially important in maths, where modern nueroscience tells us that everyone has an innate ability to do well in math. In the below video, Professor Jo Boaler explains how to succeed in learning through growth.

Below is the grading system using this course, which is based on the standard postgraduate taught conceptual equivalent grading scheme of the School. To get an above-average mark students must show a maturity in their learning and understand far beyond rote memorising.

Grade Range What you need to demonstrate What moves you up within-grade band
80-100 Thorough and systematic knowledge and understanding of the module content. A clear grasp of the issues involved, with evidence of innovative and the original use of learning resources. Knowledge beyond module content. Clear evidence of independent thought and originality. Methodological rigour. High critical judgement and a confident grasp of complex issues. Originality of argument
70-79 Methodological rigour. Originality. Critical judgement. Evidence of use of additional learning resources. Methodological rigour
60-69 Very good knowledge and understanding of module content. Well argued answers. Evidence of originality and critical judgement. Sound methodology. Critical judgement and some grasp of complex issues Extent of use of additional or non-core learning resources
50-59 Good knowledge and understanding of the module content. Reasonably well-argued. Largely descriptive or narrative in focus. Methodological application is not consistent or thorough. understanding of the main issues
40-49 Lacking methodological application. Adequately argued. Basic understanding and knowledge. Gaps or inaccuracies but not damaging. Relevance of knowledge displayed
0-39 Little relevance material and/or inaccurate answer or incomplete. Disorganised and irrelevant material and misunderstanding. Minimal or no relevant material. Strength of argument

Self Study

Much of the content for this course is self-contained within the lecture and online canvas notes. Where you find a gap in your background knowledge, you may also wish to consult one of the following texts and the relevant papers referenced in the course plan.


ID Type Name Sources
B1 Core Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: principles and practice online version
B2 Core Tsay, Ruey S. 2014. An Introduction to Analysis of Financial Data with R. John Wiley & Sons. 5 copies available in QUB library
B3 Core German,Hill & Vehtari 2020., Regression and Other stories
B3 Advanced Kennedy Peter 2008 “A Guide to Econometrics” Cambridge Press 6th Edition
B4 Advanced Fabozzi, Frank J., Sergio M. Focardi, Svetlozar T. Rachev, and Bala G. Arshanapalli. 2014. The Basics of Financial Econometrics: Tools, Concepts, and Asset Management Applications. John Wiley & Sons. QUB library online copy
B5 Recommended Spiegelhalter, David. 2019. The Art of Statistics: Learning from Data. Penguin UK

Tentative schedule

Weeks Topic Reference chapters
1 Rethinking financial econometrics B11,B31-4
2 Exploring real and fake data B11,B23,B26
3 Statistical forecasting toolkit B13
4-5 Regression and other stories B15
6 -7 linear time series regression models B12,B14 B16-8
8 Exponential smoothing and dynamic regression models B12,B26-8,B45
9 Volatility models B14 ,B211
10 Financial machine learning and econometrics B412
Barry Quinn
Barry Quinn
Director of Finance and Artificial intelligence laB FAB