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

Biography · Medical statistics

Prof. Jane Hutton

Professor of Medical Statistics at the University of Warwick. Long-standing experience in statistical evidence in medical-legal contexts. Her public commentary on the Letby shift-rota chart applies the RSS post-Sally-Clark framework in operational detail.

Medical statistics
UK
Last updated
4 min read

Why her commentary matters

Prof. Hutton’s specific research area is the intersection of medical statistics and medico-legal practice. She has testified in statistical-evidence matters in other UK criminal proceedings, and her professional experience of what judges and juries need to understand about statistical reasoning is substantial. Her public commentary on the Letby shift-rota chart is therefore not abstract — it is applied.

Professional background

  • Professor of Medical Statistics, University of Warwick.
  • Peer-reviewed publication record in medical statistics, survival analysis, and statistical evidence in medical-legal contexts.
  • Sustained public-engagement track record on statistical reasoning in medical and legal contexts.

Her analysis of the shift-rota chart

Prof. Hutton’s public analysis of the Letby shift-rota chart makes several operational points:

  • The chart conflates rate and count. A nurse who works more shifts will, on a uniform per-shift-probability model, be present at more events simply through attendance. The Letby chart did not adjust for attendance rate.
  • The chart’s denominator is wrong. The denominator should be all events on the unit; the chart used only the selected-as-suspicious events. This is the Texas-sharpshooter problem in statistical-evidence form.
  • The chart does not apply a null-hypothesis-testing framework. Statistical inference requires comparison to a null model. The chart presented an observed pattern without the baseline comparison that would be needed to assess its improbability under null.
  • The chart cannot support the inference the Crown drew from it. Pattern-matching in retrospect against a selected subset cannot rule out chance or cluster-of-correlated-events explanations.

Why statistical-community consensus matters

The Letby statistical evidence is not supported by any published peer-reviewed statistical analysis defending it against the Gill/Green/Hutton/Fenton/Spiegelhalter critique. The statistical-community consensus has settled on the critique side. This is the operational form of what the Cannings principle addresses: reputable experts disagree, and the criminal-law standard for conviction requires more than the Crown’s expert’s opinion alone.

Read alongside