Skip to content

April 2026: Thirlwall Inquiry final report due after Easter · CCRC still reviewing 31+ independent expert reports · Shoo Lee Panel (Feb 2025): no medical evidence of deliberate harm.

Lucy Letby Facts
Public commentary — summary
·Sir David Spiegelhalter; University of Cambridge

Sir David Spiegelhalter — public commentary on Letby statistical evidence

A summary of Sir David Spiegelhalter's public commentary on the Letby statistical evidence across broadcast interviews, articles and academic-forum contributions from 2023 onwards. Spiegelhalter's framework — make the denominator explicit, distinguish probability of evidence from probability of guilt, model competing hypotheses — applies the RSS post-Sally-Clark principles in accessible form to the Letby shift-rota chart. His conclusion is that the chart fails each principle.

Last updated
11 min read

Licence: Publicly released

Original source: statslab.cam.ac.uk

Mirrored on this site:

Publicly released material, attributed to its original publisher.

Context

Sir David Spiegelhalter, Emeritus Professor of Statistics at Cambridge and past president of the Royal Statistical Society, has made sustained public commentary on the Letby statistical evidence across broadcast interviews, newspaper articles and academic-forum contributions from 2023 onwards. As the UK’s most widely recognised statistical-communicator voice, his commentary has cut through to audiences that specialist academic work does not reach.

The Spiegelhalter framework in outline

  1. Make the denominator explicit. A pattern is only informative against the denominator it is drawn from. Implicit denominators produce selection-effect problems.
  2. Distinguish probability of evidence from probability of guilt. The prosecutor’s fallacy confuses P(evidence | innocent) with P(guilty | evidence).
  3. Model competing hypotheses. A statistical analysis that models only the prosecution hypothesis cannot discriminate between it and the alternatives.

How the Letby chart fails each principle

  • The shift-rota chart’s denominator of non-selected events was implicit.
  • The probability of shift-overlap given innocence was treated as probability of guilt given shift-overlap.
  • The natural-cause and systems-failure alternatives were not formally modelled.

The statistical-communication dimension

Spiegelhalter’s particular contribution is pedagogical: he makes the statistical critique accessible to non-specialists. For a CCRC review, the Court of Appeal, and the wider public audience, his framework is the bridge between specialist statistical argument and lay comprehension. The specialist critique is the same critique Gill, Green, Hutton and Fenton have developed; Spiegelhalter’s framing communicates it.

Read alongside

Sir David Spiegelhalter — biography, The Bayesian framework, The Sally Clark parallel, Statistics deep-dive.

Related on this site

Attribution and licence

Sourced from statslab.cam.ac.uk . Mirrored on this site on 2026-04-22 with attribution to the original publisher.