The off-shift collapses — walkthrough of the missing denominator

A walkthrough of the selection-bias problem in the prosecution's 25-event shift chart. The chart was constructed by selecting events at which Letby was present and then plotting her presence as the inferred pattern. Collapses on shifts where she was not on duty across the 2015-2016 cluster period were excluded. The piece covers the Texas-sharpshooter selection effect, Prof. Richard Gill's published critique, Prof. John O'Quigley's proportional-hazards reanalysis (which produces ~10% anomalous-presence probability when hours-worked is properly controlled), and the Royal Statistical Society's 2022 report and 2024 statement specifically naming this selection effect. The triedbystats.com interactive model lets readers see the chart for any nurse on the unit if the selection were not pre-restricted.