A screenshot of a cell phone

Description automatically generated

https://www.bbc.co.uk/news/health-50290033

Thanks to researcher, Legerwood, for alerting me to this.

In yesterday’s big piece 11 charts on why the NHS matters in this election by Nick Triggle and Ben Butcher, the writers make an astonishing, beginner’s error in the use of statistics, with the effect of exaggerating NHS England’s A&E performance and reducing the gap with that of NHS Scotland. The error is simple. They mistakenly use the performance figures for ‘All’ A&E departments when they should only use those for ‘Type 1’ departments in England:

Type 1 A&E department: a consultant-led 24-hour service with full resuscitation facilities and designated accommodation for A&E patients.

‘All’ A&E types, include Minor Injury Units and Walk-in Centres.

https://www.england.nhs.uk/statistics/statistical-work-areas/ae-waiting-times-and-activity/ae-attendances-and-emergency-admissions-2017-18/

Only Type 1 data are comparable with those elsewhere in the UK and are reported discretely by NHS England for that purpose.

So, for September 2019, only 77% of patients were seen in 4 hours, in Type 1 NHS England departments, while in Scotland 89.3% were!

https://www.isdscotland.org/Health-Topics/Emergency-Care/Publications/2019-11-05/Summary/index.asp

https://www.england.nhs.uk/statistics/statistical-work-areas/ae-waiting-times-and-activity/ae-attendances-and-emergency-admissions-2019-20/

I think Triggle and Butcher need a new graph.