The Department of Statistics' research is concentrated in four key areas; data science; probability in finance and insurance; social statistics; time series and statistical learning.
Research in data science area is concerned with the development of new machine learning and statistical methods, and their applications. Data science plays an essential role in modern society allowing us to understand various real-world phenomena by using scientific methods that combine statistics, data analysis, machine learning and related methods.
Members of the data science research area work on pushing the boundaries in developing new machine learning, statistical and computational methods that can extract knowledge and insights from big data, including structured, unstructured and massive volume data. We regularly collaborate with various industrial partners and other end users of data science.
Our research in probability in finance and insurance covers diverse aspects in quantitative modelling in finance, insurance, and risk management. Current areas include robust models on option pricing; model-uncertainty in decision making; valuation financial derivatives with exotic features; equilibrium with market constraints and informational asymmetry; optimal trading with micro-structure noise; insurance securitisation; contagion in financial and insurance markets; modelling energy and commodity markets.
Research in social statistics is concerned with the development of statistical methods that can be used across the social sciences. Statisticians play an essential role in all aspects of social inquiry, including: study design; measurement; data linkage; development of statistical models that account for the complex structure of social data; model selection and assessment.
Members of the social statistics group have interests in statistical methods in each of these areas and regularly collaborate with social scientists whose questions motivate new lines of methodological research. We have experience in a range of social science disciplines, including demography, education, epidemiology, psychology and sociology.
The Department's research in time series and statistical learning encompasses many aspects of these disciplines. We are keenly involved in both theoretical developments and practical applications. Current areas of interest include time series (including high-dimensional and non-stationary time series), data science and machine learning, networks (including dynamical networks), high-dimensional inference and dimension reduction, statistical methods for ranking data, spatio-temporal processes, functional data analysis, shape-constrained estimation, multiscale modelling and estimation and change-point detection.
The Centre for the Analysis of Time Series (CATS) is affiliated with the department. The centre aims to ddress the question of data analysis using both physical insight and the latest statistical methods; focus on non-linear analysis in situations of economic and physical interest, such as weather forecasting; promote awareness of limitations of non-linear analysis and the danger of blindly transferring well-known physics to simulation modelling; focus on end-to-end forecasting, taking account of current uncertainty about the state of the system, model inadequacy and finite computational power.