Covid-19 cases and the weekend effect

There’s significant mounting interest in the increase in detected cases in the UK. However, it’s worth looking at the data to try and understand what is going on.

First, it is essential to analyse cases by the date the specimen was taken, as opposed to reported. The second vital thing to do is to observe this data for emerging patterns, even before looking at the numbers.

If you do this, then the Government’s Staging Data shows an emerging pattern, whereby the number of people testing positive on the weekend is significantly lower than that observed in the week. Furthermore, if you assess the data for the last week, you see this effect is accentuated by the Bank Holiday Monday on 31 August.

This suggests people would rather not come forward for testing on the weekend or, alternatively, the system has less capacity at the weekend, meaning it is more challenging to get a test. Undeniably, viruses work seven days a week; so, are people waiting till the Monday to get their test done, or is the system just not up to it?

This weekend effect pulls down the seven-day moving average – and looking at the low numbers on the weekend might give you a false sense of reassurance. This is because it seems cases are down, and therefore elimination of the virus is possible. But, unlike our population, viruses do work weekends.

Suppose you remove the weekend effect, by standardising the cases numbers to the previous Friday’s results. In that case, you get fewer troughs in the data and observe numbers have been much higher than considered throughout August.

The Office for National Statistics Infection survey data has already told us this is the case. An estimated 27,000 people – and as many as 37,000 – in England had Covid-19 during the week from the 19 to 25 August 2020. Yet, government testing only picked up 6,900 over this same period, less than one-fifth of the upper number of infections predicted by the survey data.

What is damaging, at this time, is advice that jumps to rash conclusions; the data is not exponentially rising. Will cases rise as we go into winter? Yes, as they will for all acute respiratory pathogens. In a good year, they will increase about fourfold between now and Christmas; in a bad year, about eightfold.

Could the bank holiday have, therefore, facilitated the increase due to delays in those coming forward for testing? It would seem the testing is not functioning seven days a week, unlike Covid-19.