Statistical Models Can’t Predict the Future


From Dan Denning in Charm City:

Same story, different continent. Or is it, different continent, different story altogether? Your editor is still working out what day it is and what time zone he’s in. Your body tells you it’s time for a cheeseburger. But your brain tells you it’s six a.m. Confusing. We’ll push on and do our best to make sense out of today’s news.

From the looks of things Aussie stocks got the week off to a rip-roaring start. Stocks were up over 1% in Australia on Monday. You could take your pick of “reasons” why. For example, gross operating profits in corporate Australia were up 2.2% in the last quarter according to the Australian Bureau of Statistics, on a seasonally adjusted basis.

Now, if you have infinite patience, you can read how the ABS makes its seasonal adjustments on this data series in notes 17-20 here. We read it three times and still don’t really understand it, except for the part about how interest rates or other events can affect profits in a way that the statistical models can’t anticipate.

You could proceed to rubbish the statistical models for being unable to predict the future. But models aren’t people. They are designed by people, however. And the fact that a model can’t anticipate something like the GFC shows you how limited our powers of foresight are as a species.

But we do know that financial markets are getting more volatile in recent years, not less. Is it globalization? Is it the digitalization of trading data and continuous, algorithmic trading models? Does the pursuit of an informational advantage (or the belief that one is possible) drive people to trade more?

Who knows? But our guess is that the amount of uncertainty in a system multiplies with the addition of more people. This fits roughly with the idea that the more networked the world’s markets are, the more unstable they become. That is not a good sign.

But what does any of this have to do with the ABS release on corporate profits? We’ll get to that in just one minute. But to be pedantic, gross operating profits are just another way of saying net sales. Gross operating profits are not the same as net income. Net income is what you get after you back out silly old expenses like payroll, taxes, and your fixed and variable overheads.

You can wrap all that up by saying the ABS number probably tells you very little – or actually misinforms you – about whether Australian firms are getting more or less profitable. The argument for less profitable is easy to make: rising interest rates and stretched consumer wallets.

But wait, you say! Housing prices are going. Business investment has increased. Households are adding valuable new houses to their personal balance sheets and businesses are adding capital assets to their balance sheet. This is a country getting richer!

Maybe. Or maybe it’s a country levering up to buy assets again. For example, in another ABS release we learn that the country’s net debt figure has reached a new all time high, both in nominal terms and as a percentage of GDP. The net debt (public, private, household) is $647 billion. It was up $14.2 billion in the December quarter and his over 60% of GDP.

Whether this matters or not depends on who you ask. For example, the current account deficit – also released recently – came in at a booming $17.5 Billion. That’s 5.5% of GDP. But there’s a whole school of thought in Australia that it doesn’t really matter. A resource-producing economy is bound to import heaps of capital goods. As long as you take what you buy and make more money on what you produce – helped along by a favourable terms of trade where you get paid for more what you sell and pay less for what you buy – everything’s groovy baby.

But the basic assumption in this scenario is that the borrowed money is productive investment. Maybe it will be. Maybe it won’t be. You’d expect an Australia gearing up for another mining boom to increase capital goods and industrial transport equipment. It did both in the quarter.

Yet the surprising thing about the whole report in the current account deficit is in its composition. The goods and services deficit, which includes capital goods, was just over $6 billion. But the larger part of the deficit was what the ABS calls the “primary income deficit.” That grew too and was $11.2 billion in the quarter.

Now according to the IMF, primary (or factor) income is made up of repayments and dividends from your loans or investments. You’d gather, then, that a primary income deficit means you’re paying out more on foreign investments in you than you’re getting paid on your investments overseas, give or take a few nuances. So what?

Well, to borrow a line from Michael Sutchbury in today’s Australian, the persistence of the current account deficit and the large primary income deficit mean that Australia’s “Domestic savings are not large enough to finance the mining boom.” The country is going to have go deeper into debt just to mine what China wants – and that itself assumes that China’s resource wants are endless and growing.

For now the country is in the sweet spot. So much so, that everyone is expecting the Reserve Bank to raise the cash rate to 4% when it meets later today. If he raises rates now, Glenn Stevens will be the first central banker to raise rates this year. Trail blazer and rate raiser.

It will be seen and sold as good news. You have an economy that was hurt less by the GFC, apparently, than other countries. And we’ll always have China, won’t we?

But the net foreign debt and current account deficit are a reminder that much of Australia’s current prosperity – from house prices to mining profits – comes via borrowed money. Of the $647 billion in net foreign debt, $426 billion – or 65% – is owed by Australia’s financial corporations.

So what did those banks get for their buck? A bunch of dodgy mortgages and shopping malls? Or something on which to build the long-lasting wealth of the nation? We’ll find out soon enough (maybe even tomorrow!).

Meanwhile, your editor has completed phase one of his “Operation Exodus.” Our U.S. bank required us to travel all the way to the branch where we originally opened our account in order to obtain the privilege of wiring money on-line. You can presume this draconian requirement is meant to discourage people from transferring money – in this case out of the country.

And it’s not just American banks eager to hold on to their capital. Tomorrow, we’ll tell you about a subsidiary for a major Australian bank that has told investors they can’t have their money…for another for years. Until then…

Dan Denning
for The Daily Reckoning Australia

Dan Denning
Dan Denning examines the geopolitical and economic events that can affect your investments domestically. He raises the questions you need to answer, in order to survive financially in these turbulent times.


  1. “Prosperity” – local asset prices or local income? The former having been in play 3 decades with only a momentary blip in the early 90’s is proof that “mark to fantasy” can be prolonged indefinitely if the external debt volume is unrestricted.

    “65% – is owed (foreign debt) by Australia’s financial corporations” And the composition of these “financial corporations” lending books is composed of what? Well it is way underweight in capital equipment lending, and by world standards it is way below OECD country standards for bias toward business sector lending as a whole. Ask where BHP gets their money? (A: direct sourcing from offshore bond markets), and how did ASX listed companies cut their gearing ratio’s? (A: by hitting their shareholders in capital raisings – no 4 pillar banks to be found holding up existing short term credit there – but these same 4 pillars wealth management customers and their balanced super was mandatarily conscripted through Chinese Walls to bail out the banksters real estate lending biased balance sheets).

    “and pay less for what you buy” well that is what everyone in the world did when they imported deflation from China. But that is well and truly over isn’t it? Chinese GDP is not being built on exports getting back to boom levels but of rising prices & incomes locally that are now turning into higher Chinese export prices for consumer goods. While ships were fairly full in the past quarter, there was a substantial consolidation in the vessel loops in the prior two quarters (less ships). Less ships means less volume, and combined with higher imports by value means higher import prices which means importing inflation rather than importing deflation of the past decade and a half (that help keep the crony bankster run fairy land CPI basket looking rosy … well at least put cream on top of its cake (being the ponzi market moving ignorance of the CPI exclusion of rent and mortgage inflation from household outgoings at the same time)

    “You’d expect an Australia gearing up for another mining boom to increase capital goods and industrial transport equipment. It did both in the quarter.” And those purchase decisions were made in the boom, these order cycles don’t get made in a half year let alone a quarter. And just like the market was surprised by the Toll report, the last two Caltex reports on industrial diesel and a lack of accounting for the resources inventory mountains in China all seem to slip under the fat cat resource company ceo’s radar. It seems like John Schubert style corporatist flim flam still has some weight in the sector even if they laughed off his tilt at the BHP chair. Better to track BLY’s equipment hire rates to sift ivory tower stupidity from reality.

    So what we have is the reporting season where Harvey Normans and JB Hifi’s tell you how they made the illiquid wholesalers pay for the bust early last year by bashing down prices, and then took advantage as the govt stimulus kicked in to hike margins. But now they have run out of cut priced inventory, the CPI basket looks sicker, the RBA responds and ponzi Australia goes into the vice. The banks haven’t got to round two with capital constricted by a dearth of foreign funding and a hike in both risk ratios and price, and the bad loans hitting at the same time (yes we did notice how so much of the earnings bounce in the banksters last reports were from writing down bad debt provisions on long loans funded short – and what has changed for the better on the foreign funding? – zilch on the positive side and a great big number to equal some BIS negotiated bodgy average of the PIIGS/STUPIDS/US pain on the negative)

    And Labor is now stuffed because they failed with their ETS propaganda and could only have held government by going early.

    And where has emporer Ken Henry gone? Hundreds of glossy pages of drivel has gone missing.

    And on the war front

  2. Ross: “And where has emporer Ken Henry gone? Hundreds of glossy pages of drivel has gone missing.”

    Rest assured we’ll see the KHR revealed just prior the election, Ross! :)

    Biker Pete
    March 2, 2010
  3. My personal theory for why volatility is increasing (feel free to diss it) is that the amount of money around the economy that represents investment has gone up – case in point would be just after the Lehman fiasco, how the $A dropped to about 60c as the carry trade unwound. Whereas on the face of things, I’d have expected the US dollar to drop (given that they were the ones with the economic catastrophe). Perhaps its investment cash supported by debt, perhaps its my super dollars at work, and perhaps its generated by the various Reserve banks, or perhaps I can blame Goldman Sachs – either way I think the proportion of the money supply being invested by major forces is much less predictable than the money being used by individuals. An individuals spending on commodities is roughly predictable, whereas (say) Goldman may just suddenly turn around and bet its cash on oil futures to jack up the price, suddenly dropping its “demand” for tin or pork bellies or grain.

  4. First off the etymology of the word ‘STATISTICS’ , means “The Science of The State”, so you shouldn’t be surprised where this post is headed……

    “There’s Lies, Damn Lies, and then there’s Statistics”…

    A fallacy in the law of large numbers and the ‘probability of death’ was pointed out by Richard Von Mises in his PROBABILITY, STATISTICS and TRUTH which entails people jumping to rather unreliable conclusions… (not to be confused with Ludwig Von Mises other cousin D.A. Gilles and his OBJECTIVE THEORY OF PROBABILITY)

    Using figures of 1,000,000 people and 23 different insurance companies they calculated a ‘relative frequency of deaths’ as 940:85,020=0.01106 for 41y.o. insured persons.

    Now where it get’s interesting is people assume that means the chances of a 41 year old dying in the next year is .011. Which is incorrect. It might be adequate for an Insurance Company to calculate rates based on that ‘collective’. But as individuals there are other factors, and we all will belong to different statistical ‘collectives’.

    It might help someone calculate relative risk. But it’s really not a valid statistic to apply to individual cases. When it comes to “adjusting for other factors”, frankly the math involved in accounting for just a single variable is a bit of a stretch, I don’t know. When there’s multiple factors at play, I going to state my opinion as: At best, it’s a guess. And usually, it’s plain wrong.

    Moving on to the LOTTERY… Hey! wasn’t that suppose to pay for educastion ?

    Okay! Buy 1 lottery ticket, have one chance,” buy more and increase the odds ?” Buy 2 tickets and DOUBLE your chances ? Buy 3 and TRIPLE ? Actually using the classical approach(Richard) if the odds are 1:1,000,000 the chances of winning are: .000001, when you buy 2 tickets the odds increase to 1:999,999 =.000001 even if you use 2:1,000,000 your odds increase to a staggering .0000002.

    Now looking to the Objective Theory, it can be said in plain english. There’s only one winning number therefore buying more than one ticket can’t improve the odds. You only have one chance (only one winning number) so it’s a waste to buy more than one ticket.

    Moving on to the war on tobacco. Looking at the facts, alcohol is more damaging than cigarettes, and if there really was a public health concern, alcohol should be banned instead. I love to pull this one on my ‘drug warrior’ friends.

    Is alcohol safe or healthy ? NO. “But we have scientific proof: the government told us so..”

    While there is undeniable empirical evidence that smoking damages the esophageal cells, is this caused by those dirty cancer sticks or ‘total particulate dust matter’ ? In fact, your better off moving out of a polluted area than quitting smoking.

    Do both, please, but then the booze is going to get you.

  5. There is a great book you can buy called “How to lie with statistics” It’s an old book, from 1954, but gee it’s funny and well written. This is why we need our daily reckoning so much- they are the only ones who tell us the truth. If we relied on the media for information, we would all seriously be in trouble!! Thanks deaily reckoning, we love you!!

    March 8, 2010
  6. “Do both, please, but then the booze is going to get you.” – Wondered why when I did that life expectancy test 3 years ago at age 48, it told me I could expect to croak at 49. :)


Leave a Reply

Letters will be edited for clarity, punctuation, spelling and length. Abusive or off-topic comments will not be posted. We will not post all comments.
If you would prefer to email the editor, you can do so by sending an email to