MT4527 Time Series Analysis
Academic year
2024 to 2025 Semester 2
Curricular information may be subject to change
Further information on which modules are specific to your programme.
Key module information
SCOTCAT credits
15
SCQF level
SCQF level 10
Availability restrictions
Not automatically available to General Degree students
Planned timetable
10.00 am Mon (even weeks), Tue and Thu
Module Staff
Dr R C Pinto Borges
Module description
This module provides an introduction to univariate linear times series models (ARIMA processes) and univariate non-linear times-series models (ARCH and GARCH). The syllabus includes: forecasting methods for constant mean and trend models, the ARIMA class of models (including seasonal ARIMA models), fitting and forecasting ARIMA models, ARCH and GARCH processes.
Relationship to other modules
Pre-requisites
BEFORE TAKING THIS MODULE YOU MUST PASS MT2508
Assessment pattern
2-hour Written Examination = 100%
Re-assessment
Oral examination = 100%
Learning and teaching methods and delivery
Weekly contact
2.5 lectures (x 10 weeks) and 0.5 tutorial (x 10 weeks).
Intended learning outcomes
- Understand basic concepts related to Time Series modelling such as `white noise?, `stationarity?, and the autocorrelation function
- Estimate the trend and seasonality within a data set, and perform forecasting using basic Time Series models such as the Constant Mean model and the Random Walk model
- Fit to the data more complex models such the Moving Average and Autoregressive processes, as well as the more encompassing ARMA and ARIMA models
- Use R packages to utilise ARMA and ARIMA modelling to forecast future observations, evaluate the associate uncertainty, and perform model comparison
- Fit ARCH and GARCH models to estimate volatility and forecast future observations for asset return data