Hello and welcome to More or Less. We're the programme that gives dodgy statistics a

hard stare that would make Paddington bear proud of us and I'm Tim Haafard. On November

21st this claim was making the rounds.

There are more deaths in vaccinated than unvaccinated. Is the right policy to vaccinate low-risk populations?

The claim was illustrated by a chart based on data from the UK's Office for National Statistics

and did indeed show that in England for people between the ages of 10 and 59 more vaccinated

people died than unvaccinated. Wait a minute.

I don't think it means what you think it means.

Members who are both loyal and vermorious will remember a tricky little statistical phenomenon

called Simpson's Paradox.

We discussed this topic in 2016 with Charlotte McDonald, but like Bucket hats and flares,

it's back and this time weaving its pesky confiscations around that misleading fact about

vaccination. So I spoke to Stuart McDonald, actually by day, statistical sleuth by night

to find out more.

So I came across this chart at the weekend doing the rounds on social media. The chart showed

death rates from any cause for people aged 10 to 59 and it showed vaccinated and unvaccinated

death rates separately. Death rates naturally varied from one week to the next as you might

expect, but the one consistent pattern was that for the last six months death rates for

vaccinated people were higher than for unvaccinated people.

Instant red flags, we know that vaccines work. So what was going on?

I was immediately skeptical about the chart as it seemed to disagree with all the evidence

that I've seen and that you've seen that vaccines significantly reduce the risk of serious

...