- 9-10am Monday Lecture in LB01 Lloyd Building
- 4-5pm Monday Lecture in LB01 Lloyd Building
- 10-11am Friday Lecture LB04 Lloyd Building
5 ECTS module corresponds to about 100-125 hours of study time. This includes the several hours of lectures (30+ for undersgrads, 20+ for postgrads) organised on campus that students have to attend. The new academic year structure is dense and good time management is essential.
Contacting the lecturer
A Discussion Forum is/will be opened online with Blackboard to post queries and is used as the primary tool for discussion on topics related to the course. Emails from students in my taught modules might be overlooked for logistic and time management reasons. If so, please ask questions during classes or flag this email to me directly at the end of the class.
Playing with data is an important part of Statistics modules. Help is given on this webpage for using R in the context of time series. It is advised to do this labs on your own study time to get to be familiar with using R for forecasting. An example of report written with R (*.Rmd) is also available for download on Github.
All lecturenotes may not be available electronically. It is advised to come to classes and take notes. Some incomplete Lecturenotes are available. Some additional slides and exercises are available Blackboard.
There are a lot of books on time series, forecasting in the Library that are relevant to the course. Below the first book is given as an example reference. It is available in the library and most of the time series used in the labs are explained in that book.
- Forecasting - Methods and Applications S. Makridakis, S. C. Wheelwright and R. J. Hyndman, Wiley
- Forecasting: principles and practice online book by R. Hyndman and G. Athanasopoulos
The https://t.co/S3BpRgtxUW paper with its finding that the worse Stat forecasting method was more accurate than the best of the ML ones has passed the 100,000 mark of views/downloads. None of those who have read/downloaded it has challenged its finding. We are still waiting! pic.twitter.com/3Y7iC51CXm— Spyros Makridakis (@spyrosmakrid) September 13, 2019
- W1: Introduction: chapters 1-2 Lecturenotes
- W2: Holt Winters algorithms: SES, DES, SHW+ and SHWx (Chapter 5-8 with exercises
- Assignment R1 posted on Blackboard 22/09/2019
- W3: ACF, PACF, Linear model (Chapters 3,9, 10 with exercises )
- W4: Monday 30/09 @9am Questions time (assignment R1). Chapters 9, 10
- W5:Chapters 10-13, Weak Stationarity, Yule-Walker equations
- W6: Backshift operator Chapters 14-15 and exercises
- W7: Reading week - Assignment (M) posted on blackboard
- W8: Seasonal ARIMA - beer time series
- W9: Seasonal ARIMA Chapters 17 - Examples- Assignment R2 posted on Blackboard 05/11/2019
- W10: Monday 9am Feedback for assignment R1 - 4pm lecture cancelled (replaced by personal remote Feedback for assignment R1 upon request)
- W11: Transformation of time series, and conclusion (seasonal) ARIMA models
- W12: helpdesk for Feedback assignment (M) and questions time for assignment R2
Rmd filesSome Rmd files (with R code) are available on my Github, resulting in html pages e.g.:
- AR models and Yule-Walker equations (simulation)
- Time series differencing (simulation)
- Time series analysis with Arima(p,d,q) (dowjones time series)
- MA models (simulation)
Exam/AssessmentFirst session 100% continuous assessments (see Blackboard):
- (R1) Report + R code (i.e. Rmarkdown report): Analysis of a time series using visualisation tools and Holt-Winters algorithms (35%).
- (M) Mathematics of forecasting (30%)
- (R2) Report + R code (i.e. Rmarkdown report): Forecasting competition with ARIMA models (35%).
- Repeat Exam 100% (Michaelmas term 2019)