Economic forecasting is not a science

Prashanth Perumal in The Hindu

India lost its tag as the ‘world’s fastest-growing economy’ last month as its fourth quarter GDP growth fell to 6.1%, the slowest in two years. Very few economists expected the slowdown. In fact, most waited for the economy to rebound as it quickly healed from the impact of the demonetisation of high-value rupee notes in November. Critics of demonetisation felt vindicated, particularly after GDP figures for the third quarter suggested that the shocking, overnight move to demonetise had very little negative impact.

Yet, for all the sermon delivered by the country’s punditry, the fact remains that macroeconomic forecasting is a lousy business — regardless of who makes the predictions. For one, data cannot prove or disprove any hypothesis as they do not establish causation. The mere fact that growth slowed in the first full quarter after demonetisation does not prove decisively that the slowdown was caused by demonetisation. As some have speculated, the current slump in the growth rate may be a continuation of the trend of slowing growth witnessed even before demonetisation.

Nor does the unexpectedly strong GDP growth in the third quarter prove that demonetisation has had no negative impact on the economy. The economy is a complex organism with several variables working in tandem, which makes prediction an almost impossible task. This is in contrast to the physical sciences where controlled experiments allow scientists to tease out the influence of any variable.

Two, there are no constant relationships between variables when it comes to the economy that allow for making exact predictions. So, even if economists were to dig into historical data and find the exact impact that demonetisation has had on GDP growth, there is no guarantee that it would hold in the future. For instance, people’s expectations may change which makes them adapt to a cashless economy better, thus blunting the impact of demonetisation on GDP growth.

Three, macroeconomic forecasting is focussed to a very large extent on measuring things that are fundamentally immeasurable. When it comes to measuring GDP, for instance, the price that is assigned to a good as its value is arbitrarily decided by statisticians. This happens despite the fact that the value of any good lies in the eyes of the consumer. Finally, both innocent and political biases influence the process of official data collection to calculate GDP, a fact that raises questions about its reliability.
None of this is to say that economists can make no useful predictions. But such predictions are more likely to be qualitative rather than quantitative. Any wise economist could foresee that demonetisation would have a substantial impact on the economy; simply from the premise that money greases the wheels of commerce, so outlawing it would affect demand and create chaos across production lines. But trying to quantify its impact in terms of the exact percentage points of growth that would be shaved off GDP is a futile exercise.

What's the point of economists?

Why has the failure to foresee the financial crisis stoked so much anger against the profession, asks Robert Shiller

• 
• • Robert Shiller
  • theguardian.com, Monday 19 January 2015 13.51 GMT

Bankrupt investor Walter Thornton tries to sell his luxury car in New York following the 1929 stock market crash. Photograph: Bettmann/CORBIS

Since the global financial crisis and recession of 2007-2009, criticism of the economics profession has intensified. The failure of all but a few professional economists to forecast the episode – the aftereffects of which still linger – has led many to question whether the economics profession contributes anything significant to society. If they were unable to foresee something so important to people’s wellbeing, what good are they?

Indeed, economists failed to forecast most of the major crises in the last century, including the severe 1920-21 slump, the 1980-82 back-to-back recessions, and the worst of them all, the Great Depression after the 1929 stock market crash. In searching news archives for the year before the start of these recessions, I found virtually no warning from economists of a severe crisis ahead. Instead, newspapers emphasized the views of business executives or politicians, who tended to be very optimistic.

The closest thing to a real warning came before the 1980-82 downturn. In 1979, Federal Reserve Chair Paul A. Volcker told the Joint Economic Committee of the US Congressthat the United States faced “unpleasant economic circumstances,” and had a “need for hard decisions, for restraint, and even for sacrifice.” The likelihood that the Fed would have to take drastic steps to curb galloping inflation, together with the effects of the 1979 oil crisis, made a serious recession quite likely.

Nonetheless, whenever a crisis loomed in the last century, the broad consensus among economists was that it did not. As far as I can find, almost no one in the profession – not even luminaries like John Maynard Keynes, Friedrich Hayek, or Irving Fisher – made public statements anticipating the Great Depression.

As the historian Douglas Irwin has documented, a major exception was the Swedish economist Gustav Cassel. In a series of lectures at Columbia University in 1928, Cassel warned of “a prolonged and worldwide depression.” But his rather technical discussion (which focused on monetary economics and the gold standard) forged no new consensus among economists, and the news media reported no clear sense of alarm.

Interestingly, contemporary news accounts reveal little evidence of public anger at economists after disaster struck in 1929. So why has the failure to foresee the latest crisis turned out so differently for the profession? Why has it – unlike previous forecasting failures – stoked so much mistrust of economists?

One reason may be the perception that many economists were smugly promoting the “efficient markets hypothesis” – a view that seemed to rule out a collapse in asset prices. Believing that markets always know best, they dismissed warnings by a few mere mortals (including me) about overpricing of equities and housing. After both markets crashed spectacularly, the profession’s credibility took a direct hit.

But this criticism is unfair. We do not blame physicians for failing to predict all of our illnesses. Our maladies are largely random, and even if our doctors cannot tell us which ones we will have in the next year, or eliminate all of our suffering when we have them, we are happy for the help that they can provide. Likewise, most economists devote their efforts to issues far removed from establishing a consensus outlook for the stock market or the unemployment rate. And we should be grateful that they do.

In his new book Trillion Dollar Economists, Robert Litan of the Brookings Institution argues that the economics profession has “created trillions of dollars of income and wealth for the United States and the rest of the world.” That sounds like a nice contribution for a relatively small profession, especially if we do some simple arithmetic. There are, for example, only 20,000 members of the American Economic Association(of which I am President-Elect); if they have created, say, $2 trillion of income and wealth, that is about $100 million per economist.

A cynic might ask, “If economists are so smart, why aren’t they the richest people around?” The answer is simple: Most economic ideas are public goods that cannot be patented or otherwise owned by their inventors. Just because most economists are not rich does not mean that they have not made many people richer.

The fun thing about Litan’s book is that he details many clever little ideas about how to run businesses or to manage the economy better. They lie in the realm of optimal pricing and marketing mechanisms, regulation of monopolies, natural-resource management, public-goods provision, and finance. None of them is worth even a trillion dollars, but, taken together, Litan’s conclusion is plausible indeed.

The 2010 book Better Living through Economics, edited by John Siegfried, emphasizes the real-world impact of such innovations: emissions trading, the earned-income tax credit, low trade tariffs, welfare-to-work programs, more effective monetary policy, auctions of spectrum licenses, transport-sector deregulation, deferred-acceptance algorithms, enlightened antitrust policy, an all-volunteer military, and clever use of default options to promote saving for retirement.

The innovations described in Litan’s and Siegfried’s books show that the economics profession has produced an enormous amount of extremely valuable work, characterized by a serious effort to provide genuine evidence. Yes, most economists fail to predict financial crises – just as doctors fail to predict disease. But, like doctors, they have made life manifestly better for everyone.

A go-alone Scottish economy is viable – but would it be any better?

Scots may dream of a Swedish-style state but, lacking concrete plans, Ireland is the likelier model

• 
• • Aditya Chakrabortty
  • The Guardian, Monday 15 September 2014 20.38 BST

‘Like a Rorschach test, both right and left gaze upon the saltires and the protesting crowds outside BBC Scotland, and see exactly what they want to see.’ Illustration: Daniel Pudles

A friend mails from Edinburgh: “The referendum is all anybody talks about. My mate is getting married next week and says despite that, all his dreams are about independence.” An uncle born in Rangoon, but living in London for 50 years, comes to visit with one thing on his mind: “I can’t hear enough about what’s happening in Scotland.”

Britain is in the middle of something so epic that almost everyone feels compelled to have a view on it. And like a Rorschach test, both right and left gaze upon the saltires and the protesting crowds outside BBC Scotland – and see exactly what they want to see.

For the right, this is an insurgency of the subsidy junkies: a coalition of the ungrateful, the unaffordable and the utopian, hell-bent on disrupting an order that has provided three centuries of stability. Seen from the left, this is an uprising by capitalism’s oppressed, throwing off the shackles placed on them by Thatcher’s children and the Blairite zombies they are just a vote away from a socially just Xanadu. I exaggerate a little, but – after all the afternoon rallies and midnight blogs and front-page warnings from the Queen – I’m not alone.

The fundamental point, though, is this: neither picture captures the reality. Look at Scotland’s economic profile, and it’s clear that independence would be viable. But count up the building blocks that would form the basis of a new economy, and it looks sadly unlikely that an independent Scotland would be much of an alternative to the Old Corruption south of the border.

None of the above is going to stop the no campaign from keeping the union together at all costs. Which is why this weekend’s newspapers were bursting with dreadful warnings from Deutsche Bank about how a yes vote would be “a political and economic mistake as large as Winston Churchill’s decision in 1925 to return the pound to the gold standard” or the missteps in Washington that triggered the Great Depression.

That note of alarm came from the foreword to a two-page research note issued by Deutsche. Over the year, I have read thousands of such finance-house briefings – indeed, I have dim memories from very early in my career of having contributed to a few – and can say two things about them with confidence. First, for all the numbers and letterheads, they are not the word of God. They are a cross between a commentary and a forecast: think of a horse-racing tip without the colourful names, or Simon Heffer with more graphs. The Deutsche paper fits the form to a T: the bank’s group chief economist’s remarks are less economic than political in nature. “Why anyone would want to exit a successful economic and political union … to go it alone for the benefit of ... what exactly, is incomprehensible to this author.”

Fair enough: it’s one man’s view. But the other rule of research notes is that there’s bound to be another expressing a contrasting opinion. Such as the email I received from the head of the global strategy team at Société Générale. It argues that a yes vote would lay bare the fact that, without Scotland’s oil exports, the rest of the UK simply doesn’t pay its way in the world – and so independence would see “sterling quite rightly plunge into the abyss”.

Two well-known financial strategists, two divergent views – but only one gets amplified by the media. Funny that.

To make the sort of call issued by the Deutsche economists, you would need the kind of information about who would get what share of the oil and of the UK’s debts that we just don’t have yet – because those negotiations between Holyrood and Westminster haven’t even begun. Despite that, the no camp leaps on any passing argument to support its side. Even if they are pish. You can’t argue both that a go-alone Scotland would be as overbanked as Iceland, and that RBS and Lloyds leaving spells disaster: it’s one or the other.

That said, the technicalities mean the transition to independence would be turbulent. Forget about devo max; there would be austerity max, thanks to Scotland’s budget deficit. Worried over the value of their assets, savers and companies would try to shift their money south. Thousands of business contracts would need to be redrawn.

If the Scots go into currency union with the rest of the UK, their interest rates, financial regulation and probably their tax-and-spend policies will be dictated by the entity they have just opted out of. The plan B of merely adopting the pound would be even worse, and leave banks headquartered in Scotland in need of a new lender of last resort. As Dundee-born economist Mark Blyth points out, the most sensible option, of a Scottish currency, would take about five to seven years to set up a new central bank, a new bond shop and a new tax office.

These are just the technicalities – and they already spell a decade of pain. But provided the new country’s electorate was primed for such sacrifices, they could be got through. The big question for the left, both in Scotland and the rest of the UK, is what kind of alternative economy would be built. And I can’t see that it would be so different. Adopting the pound or the euro would bind the new country into the same old hated structures. Going by SNP policies, this new small state would follow the path trod by many of its predecessors over the past two decades: cut corporation tax, sell assets and try to draw in as much foreign capital as possible. The result wouldn’t be Sweden, but Ireland: a plaything for big multinationals.

It wouldn’t be impossible to craft an alternative economic policy: but there isn’t one in place yet. Ask for one and you are pointed to the Wee Blue Book or Adam Ramsay’s 42 Reasons: both are smart, generous-minded critiques of Britain’s political economy, but they are short of concrete alternatives. Ask for an alternative to Alex Salmond and you’re shown “good bloke” Patrick Harvie. But the Green party he heads polls about as well north of the border as Ukip.

In the old days of ethnic nationalism, having a vacuum in place of an alternative wouldn’t matter so much: separatism would be an end in itself. But the yes campaign that’s emerged over the past few years is built around a civic nationalism, in which the forming of a nation is only the means to an end of progressive values. Trouble is, around the central issue of economics, there is a blank ready to be filled by the old conservatism and lobbying.

Brics miracle over as world faces decade-long slump

US Conference Board fears Brics miracle over as world faces decade-long slump

The catch-up boom in China, India, Brazil is largely over and will be followed by a drastic slowdown over the next decade, according to a grim report by America’s top forecasting body.

Image 1 of 3

China’s double-digit expansion rates will soon face, fallng to 3.7pc from 2019-2025 as the aging crisis hits. 

By Ambrose Evans-Pritchard

7:37PM GMT 13 Nov 2012

377 Comments

Europe's prognosis is even worse, with France trapped in depression with near zero growth as far as 2025 and Britain struggling to raise its speed limit to 1pc over the next three Parliaments.

The US Conference Board’s global economic outlook calls into question the "BRICs" miracle (Brazil, Russia, India, China), arguing that the low-hanging fruit from cheap labour and imported technology has already been picked.

China’s double-digit expansion rates will soon be a romantic memory. Growth will fall to 6.9pc next year, then to 5.5pc from 2014-2018, and 3.7pc from 2019-2025 as the aging crisis hits and investment returns go into "rapid decline".

Growth in India - where the reform agenda has been "largely derailed" - will fall to 4.7pc to 2018, and then to 3.9pc. Brazil will slip to 3pc and then 2.7pc. Such growth rates will leave these countries stuck in the "middle income trap", dashing hopes for a quick jump into the affluent league.

"As China, India, Brazil, and others mature from rapid, investment-intensive ‘catch-up’ growth, the structural ‘speed limits’ of their economies are likely to decline," said the Board. 

The fizzling emerging market story is a key reason why the West has relapsed this year. The world is now facing a synchronized downturn all fronts, with little scope for fiscal and monetary stimulus.

^{France slumps to bottom of the class, with Britain close behind}

"Mature economies are still healing the scars of the 2008-2009 crisis. But unlike in 2010 and 2011, emerging markets did not pick up the slack in 2012, and won’t do so in 2013," it said.

The Conference Board says Europe’s demographic crunch and poor productivity has reduced trend growth to near 1pc, though it could be worse if the region makes a hash of monetary policy and follows Japan into a "structural deflation trap". Large numbers of people may be shut out of the jobs market forever.

Germany will outperform Italy and France massively over the next five years, implying a bitter conflict within EMU over control of the policy levers. While the report does not analyze debt-dynamics, it is hard to see how the Club Med bloc could keep its head above water in such a grim scenario or stop political revolt coming to the boil.

Bert Colijn, the Board’s Europe economist, said France’s woes stem from low investment, as well as delayed austerity and reform. The reckoning will now come.

He thinks Spain will fare better since it has already taken its bitter medicine. It is expected to grow at 1.8pc for the next decade as "Schumpeterian" creative destruction clears away dead wood and unleashes fresh energy - a contentious point since labour economists argue that unemployment of 25.6pc is doing permanent damage to parts of the workforce, and therefore to economic potential.

America has a younger age profile and should eke out 2.5pc to 3pc growth until 2018, and 2pc thereafter. It has a big "output gap" of 6pc of GDP to close before it hits any speed limit, so part of this is just the effect of elastic snapping back.

^{Emerging markets deflate}

The Board said lack of demand lies behind the current global malaise, but the fading technology cycle may prove a greater threat over the long-term.

The thesis is based on work by professor Robert Gordon from Northwestern University, who argues that the great innovation burst of the last 250 years is a "unique episode in human history" and may be fading. His claims challenge the work of Nobel laureate Robert Solow - orthodoxy since the 1950s - that economic growth is a perpetual process once the right legal and market framework is in place.

The Conference Board’s forecast is starkly at odds with a report by the OECD last week predicting that China would keep growing at 6.6pc until 2030, and India at 6.7pc -- propelling the two rising powers to global dominance.

Apostles of the BRICS revolution are certain to dispute the claims. Yet there could be no clearer sign that the emerging market euphoria of the last decade has fully deflated.

Wave a banknote at a pundit and he'll predict anything

Of course it is outrageous to jail scientists for honest errors, but it is legitimate to hold them to some account

• 
• • Simon Jenkins
  • The Guardian, Thursday 25 October 2012 19.30 BST

Illustration by Satoshi Kambayashi

On the evening of 5 April 2009, Luigi Guigno of L'Aquila in Italy was phoned by a sister terrified by tremors under their village. He told her not to worry. Government experts in "the forecasting and prevention of major risks" had just been on the news declaring there to be "no danger" of an earthquake. They need not go out into the street. A few hours later an earthquake struck and Luigi, his pregnant wife, their son and 300 others were crushed to death.

This week a local judge jailed six of the scientists, not for failing to predict the quake but for giving what he regarded as reckless reassurances. He fined them £6m and disbarred them from public office. World scientists condemned the verdict as inquisitorial and medieval. Britain's Lord May said it ignored the basic nature of scientific inquiry. Luigi's relatives disagreed. A local official said simply: "Some scientists didn't do their job."

When a forester fails to predict that a tree might fall and it kills someone, he is arrested. The same goes for a train mechanic who fails to repair a carriage, a cook who poisons a customer and a builder whose house collapses. They didn't mean to kill, but they failed to forecast what might ensue from their defective expertise.

Why does the same not apply to the professional scientists, experts and pundits on whose predictive genius so much of our life depends? The answer is that they claim protection, either through (usually weak) self-regulation or by pleading Lord May's fifth amendment, that the nature of scientific inquiry exonerates them of harmless mistakes.

This week agriculture ministers were left floundering by conflicting scientific guidance on bovine TB and badgers. Transport ministers were humiliated by statisticians failing to predict revenue on the west coast railway. The Totnes MP, Sarah Wollaston, called attention to the hysterical 2009 swine flu "forecast", which panicked Whitehall into blowing £500m on dubious Tamiflu, whose test results it refused to disclose.

Yesterday we were told that the nation was recovering from a second "dip" in a recession, which its forecasters had failed to predict. This is despite government economists being served by ever more powerful computers and mathematical models. No one, to the best of my knowledge, has been called to account for this failure.

Science has rarely enjoyed greater status. Schools are in thrall to it. Broadcasters grovel at its feet, with hours of programmes devoted to children gazing adoringly at scientific researchers, depicted as funny, garrulous, lovable role models. Science has taken the place of religion in a cocoon of uncritical certainty. Those who claim the title "scientist", be it natural or social, expect to combine the immunity of diplomats and the infallibility of popes. Science is merging into scientology.

Of course, Lord May is right, that academic inquiry must proceed uninhibited by risk from error. That is what universities are for, and why they should stay independent of the state. But the Italian geologists were not doing research: they were paid to apply their expertise to keep the public safe. They were not researching, but advising. They failed catastrophically.

The truth is that there is one law for the officer class and another for the poor bloody infantry. When experts trained to detect seismic phenomena fail, their fraternity does not criticise or review their work, but treats them as innocent and relieves them of blame. If an ordinary worker miscalculates the risk, if trains crash, trees fall, rivers are polluted or foodstuffs rot, he goes to jail. The difference is not in class of error but in class of person.

Since the dawn of time, people have craved prediction against uncertainty. They have paid soothsayers, witchdoctors, stargazers and palmists. They ask journalists at parties: "Who is going to win the American election?" and seem cheated if the reply is "I just don't know."

Some people are paid to forecast. Their job is to make assertions about the future, assessing likelihood over a spectrum of certainty. When a scientist says this or that "will happen", we expect it to have greater credence than if he had merely gazed into the entrails of a sacred goose.

The worst offenders are meteorologists. A Devon entrepreneur, Rick Turner, declared last month that he would sue the Met Office for inaccurate and "persistently pessimistic" forecasts, which had cost his region millions of pounds in lost revenue. I hope he wins. The gloomy Met Office, seemingly in the pay of the outbound tourism trade, is reckless with other's people's livelihoods. The weather on the Welsh coast this summer was not ideal, but it bore not the slightest resemblance to the daily "forecast" of it on the radio. The sun shone for far more hours than it rained, yet the forecast kept people away in droves. And there was never any hint of correction or apology.

Prediction matters to people. If the variables are too great, science should shut up, rather than peddle spurious expertise. But you can wave a banknote in a pundit's face and he will predict anything you like. Of course, it is outrageous to jail scientists for honest errors, but it is not outrageous to hold them to some account. When did Lord May's Royal Society last inquire into a scientific scandal? Journalists, like bankers, are getting hell these days for their mistakes. Why let seismologists off the hook?

Predictions are hard, especially about the future

By Tom Chivers Science Last updated: August 10th, 2012

Tomorrow's weather: changeable, with a 66 per cent chance of extinction events

Yesterday I read a startling-ish statistic. A Twitter account calledUberFacts, which has around two and a half million followers, solemnly informed us that there is a 95 per cent chance that humans will be extinct in the next 9,000 years. Now, it's from Twitter, it's probably nonsense. But it got me thinking. What does it even mean?

Obviously, it means that we have a one in 20 chance of surviving to the 2,280th Olympiad, held on RoboColony 46 in the balmy Europan summer of 11012AD. But how can they possibly know that? Have they perhaps got access to other universes and a time machine, and gone forward to a thousand 11012ADs in a thousand alternate realities, and noted with sadness that only 50 such timelines contained humans?

One imagines not, or someone would have said. What they're doing is offering a prediction: if we were to run the universe 20 times, we'd probably survive once. So how might they arrive at that figure? More generally, what does it mean when sports commentators say "Sunderland have a 65 per cent chance of beating Swansea", or financial journalists say "There's an 80 per cent chance that Greece will leave the euro by the start of 2013"?

I don't have any idea how UberFacts arrived at their 95 per cent figure, because they didn't give a source. Someone else suggested it came from the Stern Review into the economic effect of climate change: I had a look around, and Stern in fact assumed a 10 per cent chance of human extinction in the next century. If we extrapolate that to a 9,000-year timescale, that's 90 centuries: 0.9 (the likelihood of not going extinct per century) to the power 90 = 0.00008, or a mere 0.008 per cent chance of survival. UberFacts were being extremely optimistic.

But we've just pushed our question back a stage. We know how we got to our 95 per cent figure (sort of). But how did we get that 0.9 in the first place?

Presumably we assess the ways we could get killed, or kill ourselves. In the journal Risk Analysis, Jason Matheny put forward a few possibilities:, including nuclear war, asteroid strikes, rogue microbes, climate change, or a physics experiment that goes wrong, "creating a 'true vacuum' or strangelets that destroy the planet".

Some of them are semi-predictable. It's not impossible to put a figure on the possibility of a fatal impact with a stellar object. If you know how many large objects are wandering around the relevant bits of solar system, you could put an estimate on the likelihood of one hitting us: a Nasa scientist put it at roughly one impact per 100 million years. You can build a predictive physical model, with known uncertainties, and come up with a figure of probability which is not meaningless. Climate models are an attempt to do something similar, but the sheer number of variables involved means that even the IPCC are unwilling to go past statements such as it is "likely" that, for instance, sea levels will rise, or "very likely" that temperatures will continue to go up: the odds of "total extinction" are not given. And as for the odds of nuclear war or accidentally creating a black hole, there's no model that can even pretend to be helpful.

That 0.9-chance-of-survival-per-century is not a mathematically arrived-at probability, but a guess (and, as a commenter has pointed out, rather a high one, since we've survived 500 centuries or so without trouble so far). You can call it something more flattering – a working assumption; an estimate – but it's a guess. And, obviously, the same applies to all the others: financial journalists aren't laboriously working through all the possible universes in which Greece does and doesn't leave the euro; sports commentators haven't created mathematical models of the Sunderland and Swansea players and run them through a simulation, with carefully defined error bars. They're expressing a guess, based on their own knowledge, and giving it a percentage figure to put a label on how confident they feel.

Is that the death knell for all percentage-expressed figures? No: there is a way of finding out whether a pundit's prediction is meaningful. You can look at an expert's predictions over time, and see whether her "70 per cent likelies" come out 70 per cent of the time, and whether her "definites" come up every time. Luckily, someone's done this: Philip Tetlock, a researcher at the University of California's business school. He has dedicated 25 years to doing precisely that, examining 284 expert commentators in dozens of fields, assessing their predictions over decades. You can read about Tetlock's work in Dan Gardner's fantastic book Future Babble: Why Expert Predictions Fail and Why We Believe them Anyway, but here's the top line: the experts he looked at would, on average, have been beaten by (in Tetlock's words) "a dart-throwing chimpanzee" – ie they were worse than random guesses.

What he also found, however, was that not all experts were the same. The ones who did worse than the imaginary chimp tended to be the Big Idea thinkers: the ones who have a clear theory about how the world works, and apply it to all situations. Those thinkers tended, paradoxically, to be the most confident. The ones who did (slightly) better than average were the ones who had no clear template, no grand theoretical vision; who accepted the world as complex and uncertain and doubted the ability of anyone, including themselves, to be able to predict it. It's a strange thing to learn: the people who are most certain of the rightness of their predictions are very likely to be wrong; the people who are most likely to be right are the ones who will tell you they probably aren't. This applied equally whether or not someone was Right-wing or Left-wing, a journalist or an academic, a doomsayer or an optimist. When it comes to predicting the future, the best lack all conviction, while the worst are full of passionate intensity.

So what does this tell us about UberFacts's supremely confident but infuriatingly unsourced "95 per cent" claim? Essentially: it's nonsense. It might be possible to make a reasonable guess at the chance of extinction per century, if it's done cautiously. But extending it to 9,000 years is simply taking the (considerable) likelihood that it's wrong and raising it to the power 90. It is a guess, and a meaningless one: in 11012AD there will either be humans, or there won't, and our spacefaring descendants won't know whether they've been lucky or not any more than we do.

But there is a wider lesson to learn than that you probably shouldn't trust huge sweeping predictions on Twitter. It's that you shouldn't trust sweeping predictions at all. Anyone who says that the euro is definitely going to collapse, or that climate change is definitely going to cause wars, or that humanity is 95 per cent doomed, is no doubt utterly sure of themselves, but is also, very probably, guessing.