Law courts have to decide whether an action or exposure to an agent such as radiation or chemical substances have lead to a personal injury. The legal systems of Canada, Australia, South Africa, Ireland and the UK have similar methods for establishing responsibility for injury. The assumption that a relative risk of at least 2 means that the substance caused the injury on 'balance of probability' is often made. A common legal approach when there is uncertainty about exposure levels for an individual claimant is to rely on confident medical opinion. Lawyers prefer not to have to address several sources of uncertainty, such as different estimates of risks associated with smoking tobacco provided by studies from different countries or by different study designs.
Statistical approaches, particularly those developed in health research, evaluate risks and causes at population levels. For an individual, there is typically a trade off between adjusting for multiple characteristics of the person and finding reliably estimates of risk.
In an important UK judgement expressed the judges' dislike of the ``use of statistics alone", and tried to distinguish between "fact probability" and "belief probability" (Sienkiewicz v Greif (UK) Ltd [2011] UKSC 10). I will explore whether this is an attempt to reduce different sources of uncertainty to a binary classification.
How might statisticians respond to experts who assert that there is no need for statistics, and that the use of large databases and AI are sufficient to answer questions about causes?
This talk will illustrate the debates with reference to high profile cases: exposure to asbestos, metal-on-metal hip replacements and effectiveness of breast cancer surgery.
