Good article. Some quotes for those who don't subscribe:
The investigation began after doctors noticed an uptick in “inexplicable” deaths on the neonatal unit, with nine deaths recorded in 2015 rather than the usual average of two. There was also a rise the following year.
But John O’Quigley, honorary professor in the Department of Statistical Science, at University College London (UCL), said it was a “serious statistical blunder” to compare the deaths to the average across the country.
Instead, he said, doctors should have compared the death rates at the worst performing trusts, which would have shown that the Countess of Chester was not an outlier.
Crunching the number shows that Burton, Mid-Cheshire, Blackpool and Burton all had similar upticks in the surrounding years.
Writing in The Telegraph, Prof O’Quigley said: “There was in fact no evidence of anything extraordinary having taken place and that the belief in an inexplicable spike is based on an elementary, and very common statistical misconception.....
.....He said the same applied to the Countess of Chester. Although deaths were high, it was not unusual compared with other poorly performing trusts.
His findings are based on data from MBRRACE-UK, an organisation set up for the surveillance and investigation of maternal deaths, stillbirths and neonatal deaths.
So they weren't comparing like with like i.e., underperforming trust, with underperforming trust.
They were instead comparing the underperforming CoC trust with other good performing trusts.