Return to homepage Skip to navigation Skip to site search Skip to main content Skip to footer


Royal Statistical Society launches new guide to prevent miscarriages of justice

25 February 2015

A new guide to interpreting expert evidence in criminal law cases - co-written by Graham Jackson who is a Visiting Professor at Abertay University - has been launched by the Royal Statistical Society (RSS).

The publication outlines best practice for the evaluation and interpretation of expert evidence in criminal justice, and illustrates the common pitfalls those not well-versed in the use of statistics and probabilistic reasoning can make.

It is the last in a series of four booklets that have been written for judges, lawyers, forensic scientists and expert witnesses to help them understand and challenge expert opinion so that proper justice can be done.

The guides include case studies where statistics have been used in court, including real-life examples of where misunderstood or misleading probabilities have led to unsafe convictions.

One such example is the case of Sally Clark, who was wrongfully convicted of murdering her infant sons because of invalid statistical evidence presented in court by the prosecution.

Sally was imprisoned for more than three years before she was acquitted. Her children had, in fact, been the victims of cot death.

Speaking about why the new guide is so important, Professor Graham Jackson said:

“Too many miscarriages of justice have been the result of the poor interpretation of evidence or of the misuse of statistics by experts.

"In the past, the way in which forensic experts arrived at their opinions could be difficult to fathom, but - thankfully - the days when an expert's opinion was taken at face-value, with little challenge from lawyers and courts, are gone.

“It is extremely important to keep in mind that, even though an expert may appear to be offering clear, apparently powerful statistics to support their opinions, the numbers quoted may, at best, be irrelevant and, at worst, be downright misleading.

“Scientists, other experts, lawyers and lay people can all be prone to misunderstanding numbers and to biases in their approach to weighing up evidence.

“All expert opinion presented to courts should be grounded in logic and should correctly utilise any relevant statistics to help the court come to a rational view of the weight of the expert evidence.

“The new guide we have written gives anyone working with expert evidence the tools they need to reach a logical and accurate conclusion about the evidence with which they are dealing, whether or not statistics have been used."

The RSS is offering hard copies of the guide free to those in the legal profession, as well as making them available online at no charge.

Those who wish to be sent a hard copy of the new guide should email with their contact details and required number of copies. Similar requests for copies of earlier guides are welcome subject to availability.


For media enquiries please contact Kirsty Cameron T: 01382 308935 M: 07972172158 E:

Notes to Editors:

The new guide is the last in a series of four publications, produced by the Royal Statistical Society’s Working Group on Statistics and the Law with funding from the Nuffield Foundation.

It is authored by:

  • Graham Jackson, Professor of Forensic Science, Abertay University
  • Colin Aitken, Professor of Forensic Statistics, University of Edinburgh
  • Paul Roberts, Professor of Criminal Jurisprudence, University of Nottingham

The four practitioner guides in the series are:

  • ‘Fundamentals of probability and statistical evidence in criminal proceedings’, Nov 2010
  • ‘Assessing the probative value of DNA evidence’, Mar 2012
  • ‘The logic of forensic proof: inferential reasoning in criminal evidence and forensic science’, May 2014
  • ‘Case assessment and interpretation of expert evidence’, Feb 2015

They are available to download on the RSS website.

The Royal Statistical Society (RSS) founded in 1834 is one of the world's most distinguished and renowned statistical societies. It is a learned society for statistics, a professional body for statisticians and a charity which promotes statistics, data and evidence for the public good. Today the Society has 6000 members around the world.

Back to News