May 29, 2020 - 7:00am
Another day, another exciting-looking correlation in the world of Covid-19! Researchers at Yale have published a preprint looking at the correlation between the amount of novel coronavirus in sewage and the number of hospital admissions three days later, and they found an almost perfect match.
Imagine you’re measuring two numbers and you want to see how much one affects the other. Let’s say height and weight. So you go and ask random people in the street how tall they are and how heavy they are. You’ll notice that, on average, tall people are heavier. But sometimes, you get tall skinny people or short fat people, so the correlation isn’t perfect.
In statistics, correlations are measured in a number called R. (Not that one.) If the correlation is perfect, so for every 1% increase in height you get a 1% increase in weight, then R=1; if there is no correlation, and height and weight vary totally randomly with no link to each other, then R=0. (It can also be negatively correlated: if one goes up, the other goes down.) You can get a sense of what different R values look like by playing this game.
The Yale researchers found that coronavirus in poo on day 0 correlated with hospital admissions on day 3 with an R=0.99. That is ridiculous. It is literally saying “if coronavirus levels in sewage go up by 300% on Sunday, you should see almost exactly three times as many people admitted to hospital on Wednesday.”
It got a lot of attention, but in any human-behaviour-related study, a correlation of 0.99 is frankly unbelievable. As Alex Danvers says in a good blog post which annoyingly scooped me as I was thinking about writing this, in psychology, an R of .1 is pretty good. Even height and weight probably only correlate at about 0.7.
Here’s what went wrong, as pointed out (and explained to me) by the indefatigable bad-science-debunker Nick Brown. They weren’t checking the correlation between the raw numbers — they were checking the correlation between correlations.
Brown uses an analogy: imagine instead of measuring height vs weight, we’d measured height vs the last digit on your National Insurance number. We’d find no correlation: R=0.
Then imagine we measured weight vs the fourth digit on your NI number. We’d find no correlation: R=0.
But then imagine we checked the correlation between those two correlations. We’d find two flat lines! They correlate perfectly! R=1!
This isn’t exactly what’s gone on, but it illustrates it. They’re comparing the correlation of virus-in-poo to time with the correlation of hospital admissions to time, rather than virus-in-poo to hospital admissions directly. That smooths the curves and makes it look like a closer correlation.
(There are other problems but this post is too long already.)
Brown pointed all this out to the authors, and they’ve taken down one hugely viral tweet and are looking to correct the preprint. In his own look at the data he finds a correlation of between 0.14 and 0.4. That’s still important and useful, if it’s real! But you can’t say “if virus in poo goes up 4x today, you’ll see a fourfold increase in hospital admissions in three days’ time.”
Addendum: The Guardian raises some very serious concerns with the Lancet study into hydroxychloroquine that I mentioned in my last piece. It’s worth noting because while it undermines my specific point about hydroxychloroquine, it very much supports my case for being wary of fast science in the pandemic.
Join the discussion
Join like minded readers that support our journalism by becoming a paid subscriber
To join the discussion in the comments, become a paid subscriber.
Join like minded readers that support our journalism, read unlimited articles and enjoy other subscriber-only benefits.
SubscribeLet us remember the Guardian’s trust is reputedly founded on Slavery money- is this true or is it a myth ? .
Who cares? The days when a self-selected and hypocritical elite could tell the rest of us what to think and expect us to doff our flat caps and say ‘aye aye yer honner’ will soon be gone for ever.
Democracy is coming.
Shutting both the titles would make the world a happier place!
The hypocrisy and double dealing of the Guardian’s business decisions should hardly come as a surprise.
Guardian Media Group, when it sold its 50% stake in Auto Trader to Apax Partners in 2008, used a tax-exempt shell company in the Cayman Islands to avoid paying corporation tax. GMG realised over £300 million in profit on that sale – yet paid not a sou in Corporation tax. This was all perfectly legal.
Over the years Guardian Media Group has invested hundreds of millions in offshore hedge funds. Keeping it under the radar and beyond the grasp of HMRC. Again, all perfectly legal.
And yet, the high-minded journalists of the Guardian love nothing more than thundering their disapproval of large multinationals – Starbucks, Apple, Vodafone etc – and the unnamed “super-rich” not “paying their fair share.”
Guardian columnists (especially Nick Cohen before his excommunication) regularly get their knickers in a bunch over such tax avoidance – though oddly never train their guns on their employer, the sanctimonious Scott Trust. Why do multinationals warrant such opprobrium whilst GMG escape any criticism? What, pray, is the difference? They too are not breaking laws, merely using every legal loophole they can find to their best advantage.
After the Panama Papers story brought a lot of this to light there were many (individuals and companies) who leapt to their own defence, suggesting that even their most opaque business dealings were legal – according to the letter of the law – yet that simply wasn’t good enough for Guardian journalists who sniffily pointed out that such obfuscation was immaterial. They might be legal by the letter of the law, but not by the spirit.
Hey ho, merely another chapter in the ongoing ‘do as we say, not as we do’ saga that is the Guardian’s entire modus operandi.
As I noted the other day, the Guardian is by far the most destructive publication in the UK. Its circulation is paltry, yet its influence is pervasive and pernicious. The Guardian has an “on-air” wing in the shape of the BBC. It is also required reading for the legions of metropolitan fauxialists who manage practically every quango and institution in the country. Not to mention that it is the go-to news source for the vast majority of the teaching profession.
So although circulation figures are ever dwindling, it informs the worldview of a great many people who influence the agenda and shape the country’s -and our children’s – future. The Britain hating, race-baiting, class-envy, history-revisionist, climate-catastrophising, woke, pc leftist clap-trap that we all complain about, is in large part down to the Guardian dripping its poison every day, thirstily imbibed by readers who influence and skew the national discourse.
The G’s ongoing narrative is wholly at odds with reality – they have a dystopian worldview and narrative predicated on catastrophism – it seems almost as though they are willing such a future into existence, Presumably so they can console themselves in a sanctimonious circle-jerk of “I told you so”.
The Guardian proudly trumpets “Comment is free… but facts are sacred”. Yet facts are so routinely ignored in favour of their preferred narrative that I wonder how the Editors still put out CP Scott’s dictum every day with a straight face.
And of course Comment is decidedly not Free on the Graunaid’s web-site. See how long a comment in suppport of, say, foxhunting, lasts before it is deleted.
Anyone who “donates” even a brass razoo to The Grauniad needs their head well examined. I agree with all your opinions and the facts are beyond dispute.
Ah the morality of the left . Sacrificing humans and families for reward.
This Observer/Guardian/Scott Trust kerfuffle has many of the elements of an episode of Midsomer. So many characters, plot and subplots. So many unknowns.
This article is inaccurate insofar as the Guardian barely has any reputation left to damage.
True enough.
It’s amusing to read lefty journalists that think that ink-stained wretchdom is a sacred trust. Maybe you chaps should transform the Guardian / Observer into a Church of Activism. Or something.
I remember back in ‘93 when the Observer effectively became the Sunday Grauniad. The late great Paul Johnson wrote at the time, “What do you Guard? For whom do you Observe?”.
Yes. I used to be a faithful reader of The Observer until it became clear, following The Guardian‘s takeover, that the paper’s ethos had been ruined by ‘progressive’ prejudice. It can never be the same as it was, but new ownership might change it for the better. We’ll have to wait and see.
“Moreover, The Guardian and the Trust are sitting on a £1.3 billion cash mountain, with millions added every year from donations by readers of its website and figures such as Bill Gates.”
Now that’s a story I’d like to read: where does the Trust/Guardian get most of its money? Apart from Gates, are any other billionaires footing the bill and why?
Ironically given its editorial enthusiasm for taxing the rest of us, the Trust was originally set up to avoid inheritance tax and has since been re-constituted multiple times to be more tax efficient since.
It’s money comes from owning print titles and investing in new media. It is very cash rich largely because it sold off assets over the last decade or so, including the Autotrader title for £600m.
The Autotrader was it’s saving at the time, the Guardian had 50% and flogged it off. It has no paywall but gets subs from it’s wokie readers and can always tap up the Lord Alli set for bigger amounts than the £15 a year most people would offer.
The Guardian doesn’t like talking about the Autotrader reading class these days, it considers them part of Hillary’s deplorable class of people.
Basically now it’s a glorified blog site wittering rather than reporting, with a shrunken news site and even more shrunken print version.
Having its stories circulated on Twitter/X (which they still are despite it flouncing off officially) is a two-edged sword as it acts as much as a don’t bother paying, as a come-on.
The Gardian goes cap in hand to its readers every day, telling them how poor it is and how much it needs their donations to keep going.
I was thinking of throwing my hat into the ring with an offer to buy both The Gaurdian and The Observer. Moreover, I would pledge to retain all existing staff and columnists. I would, however, make one tiny change by adding the strapline The Home Of Satire below the banner. None of the staff would get the joke, but then they don’t realise how funny they really are. There’s irony in that, as well as satire.
Try: off-guardian.org
The rush is probably the Guardian is still losing money and a bird in the hand is worth 2 in the bush,
Business is volatile and they are smart to take the opportunity before them.
The Guardian newspaper itself may lose money but the Scott Trust has more than enough to cover it. Guardian Media Group also includes various other profitable media businesses and a new media venture capital fund.
The simple answer is that the Trust has had a strategy of selling-off legacy media holdings for the last 15 years, including things like regional print media and local radio. Selling the Observer title is just the next step. Their online brand is already consolidated under the Guardian banner, so it makes little sense to maintain a separate Sunday operation.
The Observer seems to have made £3.4 million last year. Not very much, but still enough to make it odd that the Scott Trust might be preparing to pay the lossmaking Tortoise Media to take it away.
Still, it is clear from yesterday’s edition that Keir Starmer and Rachel Reeves are just super, so on what grounds might anyone object to the title’s acquisition by the decidedly non-lossmaking BlackRock?