Effective Bayesian Modelling with
Knowledge Before Data (Short Name: BAYES-KNOWLEDGE)
This
is a European Research Council Advanced Grant (value 1,572,562 euros
for a 4-year programme April 2014-march 2018) awarded to Professor
Norman
Fenton. The full ERC code is ERC-2013-AdG339182-BAYES_KNOWLEDGE.
The project aims to improve evidence-based decision-making in areas
such as medicine, law, forensics, and transport.
What makes it radical is that it plans to do this in situations (common
for critical risk assessment problems) where there is little or even no
data, and hence where traditional statistics cannot be used. Our
solution is to develop a method to systemize the way expert driven
causal (Bayesian Network) models can be built and used effectively
either in the absence of data or as a means of determining what future
data is really required. Working with relevant domain experts,
along with cognitive psychologists, our methods will be developed and
tested experimentally on real-world critical decision-problems.
The proposed research has the potential to both reduce at source
much unnecessary data collection and improve the results of analysis of
data that is collected. It has the potential to provide rigorous,
rational, auditable, visible and quantified probabilistic arguments to
support decision-making and recommendations in areas where currently
only ‘gut-feel’ is possible. This could lead to: more
rational and defensible strategic policy making by decision makers in
government, financial, and other organisations; better medical
diagnostics; better understanding of the impact of different types of
legal and forensic evidence. The project will enable scientists,
statisticians, medics and lawyers, to be better able to reason about
probability and understand the role and limitations of data, making
better decisions with less data.
The grant is for 4 years and it buys out 50% of Prof Fenton's
time as well as some of the time of colleagues at Queen Mary. The
project is also funding 3 postdoctoral research fellows and a part-time
programmer.
BAYES-KNOWLEDGE
website