Sign in     Like us on Facebook Follow us on Twitter Watch us on YouTube

News and Blog

Join 5000 other sharemarket traders for regular blog updates!

Browse to a category

Blog Search

The Bayesian Trap

The last two minutes is particularly useful about updating internal beliefs.



A Basic Misunderstanding

The chart below is from a site called Spurious Correlations, it takes seemingly disparate facts and matches them together to create the illusion of a positive correlation. It is a simple and effective way of illustrating the problem of mistaking causation for correlation which is constant problem in the way people both think and view data.


If you were to take this at face value you would accept that there is a link between the number of films that Nicholas Cage has appeared in and the number of people who drowned by falling into a pool. You could even stretch the data a little and suggest that these drownings were not an accident and anyone who had even seen a Nicholas Cage film would nod sagely in agreement. Now consider the chart below which looks at significant historical events and the rise of the Dow.

This rather imposing looking chart is the centrepiece of an article titled The Dow’s tumultuous 120-year history, in one chart which appears on the MarketWatch site.  The article boldly claims the following –

At its simplest, the chart proves once again that over the long term, the stock market always rises because “intelligence, creativity, and innovation always trump fear,” according to Kacher.

No it doesnt – this is mistaking causation and correlation. What the chart shows is the profound upward bias of the Dow and this is the driving force of the index moving higher. This is an example of survivor bias nothing more. The original Dow components were as follows


It is obvious that these components would change over time and that this change would drag the index higher as non performing or irrelevant issues were moved out. The notion that it is innovation that is moving the market higher is not true and can be illustrated by the simple fact that Apple arguably the most innovative technology company of recent times was only added to the index in 2015. Google whose technology permeates everyday life and Amazon who have revolutionized retailing are nowhere to be seen. The Dow has remained technology light since its inception – if technology and creativity were the drivers of the market then these new companies would be added to the index very quickly.

It is quite a simple matter to generate events stick them on a chart and say they have some significance but simply saying it doesn’t make it true. As I explored last week news and significant events tends to have a complex relationship with an index and the question of does news move markets has been answered in the negative.

The article then goes onto make the bold claim –

 Investing is more challenging than brain surgery,” Kacher told MarketWatch.

I will leave others to ponder the idiocy of this last quote.

Does News Move Markets….Sort Of…Maybe…Well No Actually

I was chatting the other day with someone who was having trouble with their trading system. Their approach was based on trading news events. Such a plan is predicated on the notion that news events move markets in certain ways and whilst this movement might not be wholly predictable it will at least generate some form of activity. Such a trading system has a single giant assumption – that news and news related events move price. If this maxim does not hold up then the system is a bust.

It has been sometime since I looked at this question and I had a vague recollection of research done in the 1980’s that looked at this question and found that news as a source of trading ideas was a bust. So armed with the dimmest of memories I went looking through my archive and found what I was looking for. David Cutler, James Poterba and Lawrence Summers produced a working paper titled What Moves Stock Prices for the Department of Economics at MIT in 1988. This paper looked at the 50 largest single day moves in the US market since World War Two – I have included the events from the original monograph below.

Event 3

If you take a cursory look at the events above you could argue that news events do move markets. However, there is a glitch in that some movements defy explanation – there is simply no event that can be seen as a casual trigger for a market move. Cutler et al stated that news events could really only be useful as an agent for movement in about half of all cases of the variance in stock price movement and in my world half is a fluke.

The interesting side issue with the work of Cutler et al is that it puts another hole in the Efficient Market Hypothesis because stock price movements according to the EMH reflect the assessment of investors to new information. If markets move without the the addition of new information to the system then something else is happening that is not explained by the EMH. And it seems in the case of broad brush analysis as performed by Cutler that prices move without any significant input.

This initial work has been expanded upon by Ray Fair at Yale University who looked at outsized movements in the S&P500 futures contract. This new work had much greater granularity to it in that it looked at five minute data, something that would have been difficult in the original work by Cutler and crew simply because the available technology would not have allowed it. Fair compared what he defined as big movements with news items emanating from the Dow Jones News Service, Associated Press and New York Times. The upshot of this investigation seemed to be that the majority of large events have no news based driver. They were only able to attribute a news item to 69 of the 1159 big moves that were examined. Recent  flash crashes seem to support this notion of significant market moves  occurring without a notional driver.

So we come back to the original assumption that news events drive markets and that these moves offer opportunities that can be traded. It would seem on the evidence available that this notion is false.

No Man Is An Island

So said John Donne and the same is true of markets. One of the most fascinating features of trading is that markets at times they display interesting interrelationships and that these relationships tell you something about the underlying emotional state of the market. Below are three markets I am currently involved in and all seem at this point in time to be telling a story about how the market is currently coping with a President – Elect who seems to have the IQ of a trout and the stability of a slinky falling down Mt Everest.


As  personal disclaimer I am currently long gold, short the USD in various iterations and my short term Dow system just threw me out from my last long position. So this is my story so it reflects my internal bias. What is interesting is that the Dow didn’t power through 20,000. I remember when it hit other “significant” numbers and it just burst straight through – there was no prevarication or hesitation. Yet at the same time the Dow paused gold began to move up and the USD Index began to move down. Whilst is is interesting to try an assemble a narrative from this – it is easier to simply trade the charts and let others build a narrative as to what they mean.

As a final point it is worth looking at how a few major markets have performed YTD – as you can see precious metals seem to be doing a fair bit of heavy lifting.



Apparently I am Not Going To Die

As a regular user of sauna’s to manage post workout soreness I am heartened by this headline.

Sauna NewsSource – Healthiest Blog

Statistics And Elections

One of the more annoying things about the US election;as if it were at all possible to list all the annoying things in one sopt is the inability of journalists to understand basic statistics. Consider the
graphic below which I snipped from the site FiveThirtyEight


Most are interpreting this as a lock for the Clinton campaign, after all it has to be because 69.9% is larger than 30%. In talking about probabilities it is often instructive to use examples that people might be able to relate to. Imagine you were playing a game of Russian Roulette. Its a simple game were you load a single round into a revolver and spin the chamber, you then point the gun at your head and pull the trigger. You have a 1/6 chance of blowing your head off. Lets assume that you are playing a more advanced version were you load two rounds separately into the gun and spin the chamber. The odds of blowing your head off is now 2/6 or 33% – this roughly equates to the chance above of a Trump victory.

The question you need to ask yourself is do you feel confident enough on the basis of this change in probability to pull the trigger. My guess is you dont, even if a 66% chance of not blowing your head off is higher than a 33% chance of blowing your head off.

Starting Dates

When I was banging on about EFT’s last week I made the point in passing that when you are looking at trading systems that the start date is everything and it is the point at which most of the fudging of results occurs. As an example I took a hypothetical passive system and began to change the starting date of the system to highlight this problem. The chart below shows a series of start dates counting down from ten years ago to today. So if I had started this system and traded it for ten years its annualised return would be 3.6%. Whereas if I had started the system seven years ago my annualised return would only be 1.1%.ReturnsAs you can see changing the start date changes the annualised return that is generated by the system. The worst returns have occurred in recent times with the best being five years ago. It doesn’t take much to work out which you might include in your marketing material if you wanted to cast yourself in the best light. This problem can occur on even shorter time frames such as moving the start date from one month to another.

The problem is also has nuance that catches the unwary; annualised returns are simply a nonsense measure when viewed in isolation because of problems with the construction of averages. For example imagine you invest $100,000 in a fund that in the first year generates a 100% return and then in the second year losses 50%. How much have you made, if you were to a look at the yearly average return you would calculate that 100%-50%/2 = 25% and the fund manager could rightly claim to make this average figure. However, your true return which is the only one that matters is zero.

True returns are given by an equity curve with as much data as possible – this gives you some idea of the trajectory of an account under a variety of conditions. This is then supplemented by looking at the drawdown curve of the system to give you an idea of how rough the ride. So for our hypothetical system above if I take the start date of 10 years ago I get an annualised return of 3.6% but a maximum drawdown of 44.5% because the system is caught by the GFC and being passive it takes no defensive action. Yet if I take our preferred kick off date of five years ago I get a drawdown of only 20.8%. So my system at this point has nearly twice the annualised return and half the drawdown.  Yet the ten year figure is the more complete since it also includes a global shock so it shows the true performance of the system whilst under pressure.

This leaves us with the problem of how to deal with this in a real world situation where this data might not be forth coming. Fortunately we can reduce this problem to a simple rule. If a system does not immediately show a drawdown or has a smooth equity curve something is not right.

General Advice Warning

The Trading Game Pty Ltd (ACN: 099 576 253) is an AFSL holder (Licence no: 468163). This information is correct at the time of publishing and may not be reproduced without formal permission. It is of a general nature and does not take into account your objectives, financial situation or needs. Before acting on any of the information you should consider its appropriateness, having regard to your own objectives, financial situation and needs.