Log in
In recent years there has been an explosion of real data from areas as diverse as bioinformatics, genetics, engineering and finance. Coupled with this has been the development of complex and realistic Bayesian statistical models to represent these data. In order to use these models to perform (Bayesian) statistical inference, one is required to calculate integrals, which are unknown analytically. Most of the numerical methods used to approximate these integrals are based upon Monte Carlo methods of which some of the seminal work has been done at Imperial College London, for instance the `particle-filter' developed in 1993 [4]. These methods are now very widely used in finance for automated trading, calculating the probability of default for economies, and for target tracking in the defence sector and we give explicit exemplars of each. The numerical methods developed at Imperial have been important in applying realistic models to these varied application areas and have impacted companies and organisations as diverse as Maple-Leaf Capital LLC, QinetiQ and the Credit Research Initiative.
A generalized additive model (GAM) explores the extent to which a single output variable of a complex system in a noisy environment can be described by a sum of smooth functions of several input variables.
Bath research has substantially improved the estimation and formulation of GAMs and hence
This improved statistical infrastructure has resulted in improved data analysis by practitioners in fields such as natural resource management, energy load prediction, environmental impact assessment, climate policy, epidemiology, finance and economics. In REF impact terms, such changes in practice by practitioners leads ultimately to direct economic and societal benefits, health benefits and policy changes. Below, these impacts are illustrated via two specific examples: (1) use of the methods by the energy company EDF for electricity load forecasting and (2) their use in environmental management. The statistical methods are implemented in R via the software package mgcv, largely written at Bath. As a `recommended' R package mgcv has also contributed to the global growth of R, which currently has an estimated 1.2M business users worldwide [A].
Impact: BEAST software has widespread applications with impacts on public health policy, service provision and awareness, and in other contexts such as commercial disputes and criminal cases.
Beneficiaries: Public agencies such as health bodies and criminal courts; ultimately, global and local populations subject to infectious disease epidemic and pandemic outbreaks in which BEAST is used to inform the response.
Significance and Reach: BEAST is critical software that has been used to understand the spread of and to inform the response to global pandemics such as H1N1 swine-flu. It is also used to determine disease origin and transmission issues in specific situations (e.g. in criminal cases). The reach of this software is therefore both global and local.
Attribution: Rambaut (UoE) co-led the phylogenetic research and developed BEAST with Drummond (Auckland, NZ). The subsequent epidemic and pandemic analyses were variously led by Rambaut and Pybus (Oxford) and by Ferguson (Imperial College London).
Since 2008, statistical research at the University of Bristol has significantly influenced policies, practices and tools aimed at evaluating and promoting the quality of institutional and student learning in the education sector in the UK and internationally. These developments have also spread beyond the education sector and influence the inferential methods employed across government and other sectors. The underpinning research develops methodologies and a much-used suite of associated software packages that allows effective inference from complicated data structures, which are not well-modelled using traditional statistical techniques that assume homogeneity across observational units. The ability to analyse complicated data (such as pupil performance measures when measured alongside school, classroom, context and community factors) has resulted in a significant transformation of government and institutional policies and their practices in the UK, and recommendations in Organisation for Economic Co-operation and Development (OECD) policy documents. These techniques for transforming complex data into useful evidence are well-used across the UK civil service, with consequent policy shifts in areas such as higher education admissions and the REF2014 equality and diversity criteria.
Reversible Jump Markov chain Monte Carlo, introduced by Peter Green [1] in 1995, was the first generic technique for conducting the computations necessary for joint Bayesian inference about models and their parameters, and it remains by far the most widely used, 18 years after its introduction. The paper has been (by September 2013) cited over 3800 times in the academic literature, according to Google Scholar, the vast majority of the citing articles being outside statistics and mathematics. This case study, however, focusses on substantive applications outside academic research altogether, in the geophysical sciences, ecology and the environment, agriculture, medicine, social science, commerce and engineering.
In a series of papers from 2003, Gibson (Maxwell Institute) and collaborators developed Bayesian computational methods for fitting stochastic models for epidemic dynamics. These were subsequently applied to the design of control programmes for pathogens of humans and plants. A first application concerns the bacterial infection Clostridium difficile in hospital wards. A stochastic model was developed which was instrumental in designing control measures, rolled out in 2008 across NHS Lothian region, and subsequently adopted across NHS Scotland. Incidence in Lothian reduced by around 65%, saving an estimated £3.5M per annum in treatment and other costs, reducing mortality and improving patient outcomes, with similar impacts elsewhere in Scotland. A second application concerns the spread of epidemics of plant disease in agricultural, horticultural and natural environments. Models developed in collaboration with plant scientists from Cambridge have been exploited by the Department for Environment, Food and Rural Affairs (Defra) and the Forestry Commission under a £25M scheme, initiated in 2009, to control sudden oak death in the UK, and by the United States Department of Agriculture to control sudden oak death in the USA.
Wavelets and multiscale methods were introduced and rapidly became popular in scientific academic communities, particularly mathematical sciences, from the mid-1980s. Wavelets are important because they permit more realistic modelling of many real-world phenomena compared to previous techniques, as well as being fast and efficient. Bristol's research into wavelets started in 1993, has flourished and continues today. Multiscale methods are increasingly employed outside academia. Examples are given here of post-2008 impact in central banking, marketing, finance, R&D in manufacturing industry and commercial software, all originating from research at Bristol. Much of the impact has been generated from the original research via software. This software includes freeware, distributed via international online repositories, and major commercial software, such as Matlab (a preeminent numerical computing environment and programming language with over one million users worldwide).
Research conducted in UCL's Department of Statistical Science has led to the development of a state-of-the-art software package for generating synthetic weather sequences, which has been widely adopted, both in the UK and abroad. The synthetic sequences are used by engineers and policymakers when assessing the effectiveness of potential mitigation and management strategies for weather-related hazards such as floods. In the UK, the software package is used for engineering design; for example, to inform the design of flood defences. In Australia it is being used to inform climate change adaptation strategies. Another significant impact is that UCL's analysis of rainfall trends in southwest Western Australia directly supported the decision of the state's Department of Water to approve the expansion of a seawater desalination plant at a cost of around AUS$450 million. The capacity of the plant was doubled to 100 billion litres per year in January 2013 and it now produces nearly one third of Perth's water supply.
With global demand for energy ever increasing, environmental impact has become a major priority for the oil industry. A collaboration between researchers at the University of Glasgow and Shell Global Solutions has developed GWSDAT (GroundWater Spatiotemporal Data Analysis Tool). This easy-to-use interactive software tool allows users to process and analyse groundwater pollution monitoring data efficiently, enabling Shell to respond quickly to detect and evaluate the effect of a leak or spill. Shell estimates that the savings gained by use of the monitoring tool exceed $10m over the last three years. GWSDAT is currently being used by around 200 consultants across many countries (including the UK, US, Australia and South Africa) with potentially significant impacts on the environment worldwide.
In response to the deficiencies in bank risk management revealed following the 2008 financial crisis, one of the mandated requirements under the Basel III regulatory framework is for banks to backtest the internal models they use to price their assets and to calculate how much capital they require should a counterparty default. Qiwei Yao worked with the Quantitative Analyst — Exposure team at Barclays Bank, which is responsible for constructing the Barclays Counterpart Credit Risk (CCR) backtesting methodology. They made use of several statistical methods from Yao's research to construct the newly developed backtesting methodology which is now in operation at Barclays Bank. This puts the CCR assessment and management at Barclays in line with the Basel III regulatory capital framework.