select search filters
roundups & rapid reactions
before the headlines
Fiona fox's blog

expert reaction to latest data from the ONS COVID-19 Infection Survey

The Office for National Statistics (ONS) have released the latest data from their COVID-19 Infection Survey.


Prof Kevin McConway, Emeritus Professor of Applied Statistics, The Open University, said:

“Most of the important findings in this week’s regular ONS release on their Coronavirus Infection Survey (CIS) already appeared in the headline release on Wednesday, though some of the findings are more clearly shown in the charts in today’s release.

“I don’t have anything to add to my Wednesday comments1 on the prevalence results – that is, the estimates of the numbers who would test positive, regardless of whether they are newly infected or have already been infected for some time.

“I will, however, say something about the incidence estimates – the estimates of daily numbers of new infections, that is, of the number of people newly infected, on average, on a given day. The latest incidence estimates are for the week ending 23 December. Prevalence estimates always appear about a fortnight after the incidence estimates for the same week, for technical reasons. Also, because they are statistically more demanding to estimate for various technical reasons, the margins of statistical error are wider than for the prevalence estimates.

“Adding up the separate ONS estimates for the four UK countries, we find that an estimated 357,600 people were infected every day, on average, across the UK that week. That’s an increase of 62% on the estimate for the week ending 17 December, just six days before. On average an additional 136,400 infections every day, on top of the already very high figure for the previous week. Even allowing for the fairly wide error margins, that’s undoubtedly a very big weekly increase.

“The rate of increase was a bit slower than the UK average in Northern Ireland, and a bit faster in Scotland, but high everywhere. For every one of the four UK countries, the incidence rate in that week was the highest that it has been since the CIS began, though it was higher in England in relation to the population size (about 60 new infections per 10,000 people per day) than in the other three countries (where, in each, it was roughly 40 new infections per 10,000 people per day).

“It’s no surprise that daily infections were rising very fast then, as Omicron really took hold just before Christmas. We saw that in the figures for new confirmed infections on the Government dashboard, which is also an incidence estimate – though the CIS is a more reliable source of information because it isn’t affected by changes in the numbers and types of people being tested routinely, or in availability of tests.

“As generally happens, the CIS figures for new infections are a lot larger than the dashboard new confirmed cases estimate. For the UK, for the week ending 23 December, the average daily number of new confirmed cases on the dashboard was about 114,600, compared to the CIS estimate of 357,600 new infections a day.

“The difference is because rather a large proportion of new infections is not picked up by the routine testing that provides the dashboard numbers. Infections often do not cause any symptoms, even though asymptomatic infected people can still spread the infection to others. Without symptoms people might not be routinely tested, and so end up not being counted in the dashboard cases. Some people might avoid testing, for various reasons, even if they do have some symptoms. Also, the CIS new infection estimates can take into account re-infections, where someone who was previously infected gets infected again (subject to a definition of what is counted as a reinfection and what might just be a continuation of an old infection). The dashboard confirmed case figures do not currently count anyone as a case if they have previously been counted as a case, so reinfections are excluded. That’s a potential problem with Omicron, because there is evidence that it is considerably more likely to infect previously infected people than was the case for previous variants.”




All our previous output on this subject can be seen at this weblink:



Declared interests

Prof Kevin McConway: “I am a Trustee of the SMC and a member of its Advisory Committee.  I am also a member of the Public Data Advisory Group, which provides expert advice to the Cabinet Office on aspects of public understanding of data during the pandemic. My quote above is in my capacity as an independent professional statistician.”

in this section

filter RoundUps by year

search by tag