Colloquium – the UK civil law approach to epidemiology/ statistical evidence

The next meeting of the section will be on 11 June at Fountain Court Chambers. We will be discussing the role of epidemiological and statistical evidence in civil law. A range of speakers will present their view and there will be time for discussion. Sign-up for this meeting is required as the number of attendees is limited. The registration page can be found here:


Date:     11 June 2018 – 2-5pm

Venue:  Fountain Court Chambers, London EC4Y 9DH

Chair:  Dr Claire McIvor


  • Practitioner’s view by Leigh-Ann Mulcahy QC
  • Judge’s view by Mr Justice Stuart-Smith
  • Legal academic’s view by Professor Jane Stapleton
  • Statistician’s view by Professor Jane Hutton
  • Epidemiologist’s view by Professor Alan Silman
  • Open discussion


To consider the approach in case-law regarding the validity and application of epidemiological and statistical evidence in UK civil law and in particular:

  • Whether, and in what circumstances, statistical evidence can be used on its own to prove causation;
  • the validity and application of the “doubles the risk” test to (a) proof of defect and (b) proof of factual causation;
  • whether there is confusion about how the civil (balance of probabilities) standard of proof operates and its relationship with factual causation;
  • whether the right experts are being used in court in relation to these issues;
  • the differences between epidemiological and statistical evidence;
  • the relevance of the Bradford-Hill criteria;
  • whether there are any gaps evident in understanding/approach between the law and statistics/epidemiology and, if so, how these might best be bridged?

 Relevant cases:

XYZ v Schering Health Care [2002] EWHC 1420 (QB)

Sienkiewicz v Grief (UK) Ltd [2011] 2 AC 229, Supreme Court

Heneghan v Manchester Dry Docks Ltd [2016] 1 WLR 2036

Metal on Metal Hip Litigation judgment (forthcoming)

Relevant materials:

ICCA/RSS guide “Statistics and probability for advocates: Understanding the use of statistical evidence in courts and tribunals” at pp.67-70:

Dr Claire McIvor: “Debunking some judicial myths about epidemiology and its relevance to UK tort law” Med.L.Rev 2013, 21(4), 553-587

Professor Jane Stapleton: “Factual causation, mesothelioma and statistical validity” LQR 2012, 128 (Apr), 221-231

Dr Gemma Turton: Evidential Uncertainty in Causation in Negligence (Hart, 2016)

Professor Philip Dawid: “The Role of Scientific and Statistical Evidence in Assessing Causality” in Professor R Goldberg (ed) Perspectives on Causation (Hart, 2011)


AGM and cyber crime meeting

The next meeting of the section will take place on Tuesday 17 October 2017 from 14.00 to 16.30 at the Royal Statistical Society, 12 Errol Street, London EC1Y 8LX.

The annual general meeting will be held from 13.40 to 14.00. Following the AGM there will be a joint meeting with the Data Science Section on cyber crime featuring talks by Professor Niall Adams (Imperial College London) and GCHQ. The schedule is below:

14:00 – 14:30 Coffee and Tea

14:30 – 15:30 GCHQ speaker. Title: Data science for security at GCHQ. GCHQ

15:30 – 16:30 Prof. Niall Adams. Title: On Constructing Cyber-Analytics. Department of Mathematics, Imperial College, London

This event is free to attend but registration is required on the following link:



GCHQ speaker

The Government Communications Headquarters (GCHQ)

Title: Data science for security at GCHQ

This talk will give a brief survey of data science for cybersecurity at GCHQ, and some thoughts on longer-term challenges for the statistics community.


Prof. Niall Adams

Department of Mathematics, Imperial College, London

Title: On Constructing Cyber-Analytics

Enterprise network defense is providing great opportunities for the development and deployment of statistical and machine learning methods. Such methods are intended to complement existing defenses, such as firewalls, virus scanners, and intrusion detection systems – which are predominantly signature-based. The role of data analysis methods is to provide enhanced situation awareness, by providing monitoring and alerting mechanisms to detect departures from “normal” behavior. In developing analytics in this context, a variety of challenging problems need to be addressed, including the volume and velocity of the data, high levels of heterogeneity, temporal variation, and more.  We review aspects of the problem and characteristics of the various data sources.  At present, the vision of jointly modelling various data sources at different levels of network abstraction, appears out of reach due to data volume and timeliness concerns. Instead, we describe a set of novel, and often simple, analytics that operate within different levels of the abstract hierarchy.


19 October – Meeting in Manchester

On Wednesday 19 October there will be a joint meeting of the RSS Statistics and the Law Section and the RSS Medical Section at the University of Manchester.

Date and time: 13.30 to 17.00, 19 October

Location: Blackett Lecture Theatre, Schuster Building, Brunswick Street, University of Manchester


A lot of research into causes of deaths for different population and patient groups use data that were not collected for such a purpose. There are particular caveats to how causes are coded within hospital and death certificate registration data that need to be acknowledged, in order to correctly interpret such analyses. The RSS Medical and Stats & the Law Sections have organised an afternoon of talks on these caveats and challenges. Confirmed speakers and talks are:

Mr. Michael Singleton (Senior Coroner for Blackburn, Hyndburn & Ribble Valley and lead coroner for the UK Disaster Victim Identification Cadre of Advisory Coroners):
“A coroner’s perspective on the conclusion of suicide.”

Dr. Peter Sidebotham (Associate Clinical Professor and Reader in Child Health):
“One to two children per week? Challenges in interpreting data on deaths from child abuse and neglect”

Prof. Tim Millar (Senior Research Fellow, National Drug Evidence Centre):
Title of talk to follow.

Dr Ben Windsor-Shellard (Mortality Analysis group, Office for National Statistics)*:
“Death certification and mortality statistics”

*Note that Ben will be speaking in place of Claudia Wells.

This meeting is free to attend, but please register at the following link:


Meeting – the role of databases in forensic science

On Tuesday 15 March, a Section meeting on the role of databases in forensic science was held at the Royal Statistical Society headquarters on Errol Street, London. We had three very interesting talks:

  • Professor Graham Jackson (Visiting Professor of Forensic Science at Abertay University and Consultant Forensic Scientist at Advance Forensic Science) and Mr Adam Baines (Forensic Specialist, Lancashire Constabulary) spoke on  “The use of databases in footwear mark cases”. The slides can be downloaded here: GrahamJacksonAdamBainesSlides,
  • Dr Tina Lovelock (Interpretation Lead, Cellmark Forensic Services) spoke on “Non-DNA databases and collections in forensic science”, and
  • Dr Ian Evett, CBE (Forensic Statistician, Principal Forensic Services) spoke on  “The logical foundations of forensic science: future challenges”. The slides for this talk can be downloaded here: IanEvettSlides. Dr Evett’s paper on this topic (which is in a special issue of Philosophical Transactions B on the paradigm shift for forensic science) can be found here:

To sign up for notifications of future meetings, you can sign up to the Section mailing list via the “Mailing list” tab.