The grid shown to the Lucy Letby jury is still the image most people remember. Across a run of collapses and deaths at the Countess of Chester in 2015 and 2016, her row was shaded every time. The other nurses on the unit appeared only in scattered boxes. Prosecutors treated the pattern as evidence that she was constantly present when the harm happened. Statisticians who have examined how the grid was built say it proves something narrower, and almost empty: that she was present at the events someone chose to put on it.

The technical objection is selection, not arithmetic. The events on the chart were not every death or collapse on the unit. They were the events that became cases. Collapses when Letby was not on duty were left off. Once the rows are chosen because she was there, her column fills by construction. Jane Hutton, professor of medical statistics at the University of Warwick, has called the material a pile of broken crockery that cannot hold water however high it is stacked. She has also said that doctors with no statistical training were allowed to give statistical opinions, and that the failure to test a roster properly is one of the ways medical-murder cases go wrong. John O’Quigley, honorary professor of statistical science at University College London, has compared the reasoning to the lottery fallacy: the chance of a particular ticket winning is tiny, so the winner must have cheated.

Peter Green, emeritus professor at the University of Bristol and a former president of the Royal Statistical Society, has called the chart a classic misuse and noted the echo of Sally Clark, whose convictions for killing her sons were quashed after flawed statistics were exposed. At a Royal Statistical Society meeting in September 2024, the rota pattern was described as scientifically worthless and, by some in the room, as a scientific fake that could not be reproduced independently. Green later told an Australian outlet there were almost too many flaws to list: errors in compilation, no proper justification for which staff and which events were included, no record of how close the babies were to one another or to possible sources of infection, and no inclusion of shifts on which nothing suspicious happened. The chart, he said, was compiled by people who already had a suspect in mind.

Private Eye’s medical columnist Phil Hammond reported that dozens of other deaths or non-fatal collapses in the relevant period never appeared, including deaths for which Letby was not on duty and was never charged. A separate modelling exercise ᴀssociated with Peter Elston, a fellow of the Royal Statistical Society, suggested that a shift toward smaller and more premature babies could produce a spike in expected deaths that looks, on a crude plot, like foul play. A Royal College review had already noted that the unit was taking more premature and low-weight infants in those years. Letby was also working more shifts than many colleagues. Police and prosecutors have said the grid was one brick in a wall, not the wall, and that clinical evidence, notes, insulin results and colleague testimony carried the case. A statistician was considered and not relied upon. The Royal Statistical Society has been careful not to declare the convictions wrong. What it has said is that the form of argument is the kind its own guidance, written after Sally Clark, warns courts against.

A bad chart does not free a defendant. It does mean that a picture which looked like certainty to a jury may have been a tautology. The commission now deciding whether the case should return to the Court of Appeal has that objection in the bundle, joined to the medical disputes. The jury did not see the missing rows.

Source: New York Post