Outlier Trades: Friend or Foe.
November 7, 2005
We're often taught in life not to trust abnormally large or small events. "It was a fluke" "It's too good to be true", "He laid an egg", "It was an aberration" and so on are all idioms which mean in one way or another that a very good or very bad result was just a one time event that is not likely to be repeated.
While the occurrence of "flukes" or outliers, as statisticians like to call them, isn't especially worrisome for your average person, they do affect our lives. Outliers like Category 5 hurricanes, 100 year floods, and earthquake are one type of example. Winning the lottery or getting a hole in one are other examples.
But should we be overly concerned with outliers as it relates to trading systems?
The $5,400+ R-Mesa 5 winning trade a few weeks ago was a monster trade that cut the system's drawdown nearly in half in the span of a few hours. Such a dramatic turn around in just a single trade is literally unbelievable, and brings to the forefront the issue of whether such outlier trades are a good thing for a trading system.
I can hear people asking how such a trade could be anything but a good thing. Who doesn't like big winners? But the possibility that such a trade is a one time anomaly not likely to be repeated is what makes such outliers problematic. If an investor decides to follow a certain trading system based on that system's statistics, but those statistics are skewed upwards by an outlier trade or two - there is the very real possibility that the hypothetical results are overstated somewhat.
So can the investor who chooses to get involved with a system that has large outliers expect such trades in the future? That is the hundred thousand dollar question, of course; and the quick answer is no. Investors should not expect to see such large winning trades, as they are statistically few and far between. We call such trades outliers.
An outlier is a statistical term. It refers to observations in a distribution of data that deviate so much from the other observations as to arouse suspicions that it was generated by a different mechanism. Statisticians hate outliers. They make their data poor fits onto their models, and are therefore normally discarded so as to get more accurate statistics.
But how should the system investor view outliers? As friend or foe. Should we remove them out of backtested results as the statisticians would have us do, throwing out the highest and lowest values to give a possibly more accurate representation of future performance? Or can we accept that outlier trades are not statistical anomalies, but real trades not only destined to happen, but indeed planned for in a system's logic.
The scary part for investors thinking they may want the outliers removed from backtesting is that trading systems do rely heavily on outliers. The table below shows a cross section of systems with the number of outliers they have had over the past 10 years, the dollar amount of profit attributed to those outliers, and the percentage of the total net profit those outliers represent. You will see that the systems in this example have relied rather heavily on outliers, with the total profit of each reliant on outliers by double digit figures.
But is this a bad thing? Many systems are designed to capture such outliers, giving them more of a long option profile. The long option profile results in a distribution of returns tightly bunched around very small losing trades, with a small number of very large outlier winning trades. A short option profile, in contrast, has many small winning trades, but a few devastatingly large losing trades. The men and women who develop systems are no dummies - they don't want a short option profile which would result in eventual devastation.
Most system developers don't set out to create a system dependent on outliers, but do so by following the simple tenet of "let winners run, while cutting losers short". This philosophy results in an abnormal distribution of trade results, where there are more "extreme" results sitting way out on the right hand of the curve than could be expected by a normal bell shaped curve. Long term, multi-market systems rely more on the "Let Profits Run" mantra than their day trading counterparts, for the main reason that the day trading systems have just a single day to let their profits run. You can see in the table above that the trend following systems Andromeda, Brix, and Aberration Plus have a much higher percentage of outlier profits.
There are such things as negative outliers, but systems avoid these like the plague. It's just not worth it to risk a very large amount on many trades for the higher probability of many small winners. If you see even a small number of negative outliers in backtested results, be worried, as such a system has most likely adopted the short option profile.
So if you see some positive outliers in your actual trading or backtested results, it should not be cause for alarm. One caveat to this can be if several outliers occur across a single time period. For example, many Nasdaq trading systems look very good in backtesting, showing hundreds of thousands of dollars in profits. Looking more closely at the statistics, however, one will find that the grand majority of such profits were attained in the NASDAQ's hay day of 100 point moves in late 1999/early 2000.
By nearly all accounts, the above mentioned time period was a speculative bubble and collapse the likes of which may never be seen again, and putting too much faith in results which owe the grand majority of their profits to that time period can lead to disappointment in the current environment where the Nasdaq range is just 20% of what it was.
So beware the abnormal conditions outlier in backtesting, but welcome with open arms the real-time outlier which pulls your system into the black for the year.
- Walter Gallwas
IMPORTANT RISK DISCLOSURE
Futures based investments are often complex and can
carry the risk of substantial losses. They are intended for sophisticated investors and are not suitable for
everyone. The ability to withstand losses and to adhere to a particular trading program in spite of trading
losses are material points which can adversely affect investor returns.
Feature | Week In Review | Chart of the Week |
Feature | Week In Review | Chart of the Week |
After a great month of October, many traders and investors were hoping to see a continuation of the volatile market conditions in November. And while last week mainly saw slow trading conditions which left day trading systems out in the cold, the generally higher trend was a good thing for most swing trading systems.
The combination of the Federal Open Market Committee meeting on Tuesday and Friday’s much anticipated Unemployment Report seemed to leave most traders on the sidelines for the week. Surprisingly the US stock market was able to grind out gains across the board with SP futures climbing +1.86%, NASDAQ futures were up +4.61%, Russell 2000 futures jumped +3.91%, and Midcap 400 futures climbed +3.78%.
In the bond markets US bond futures seem headed towards new 2005 low as the continuous ¼ rate hikes by the Fed have pressured bond prices and caused 30 year bond futures to drop by nearly 6% since early September.
The effects of the US rate hikes are being felt in the foreign currency markets as well with the US Dollar gaining strength — sending the Eurocurrency, Swiss Franc, and Japanese Yen all lower. Last week the US Dollar Index gained +1.90%, while Eurocurrency lost -2.02%, the Swiss Franc lost -2.03%, Japanese Yen was down -2.27%, the Aussie Dollar lost -2.09%, and the British Pound lost -1.27%.
Energy prices continued their recent downward trend, as the US supply outlook continues to improve each week. Last week Crude Oil prices flirted with the $60 mark all week and ended up falling -1.05%. The other energies followed suit with Natural Gas falling -9.85%, Heating Oil dropping -5.31%, and Unleaded Gas futures down -3.46%.
Finally, it was an up and down week in the grain and soft markets with Soybeans climbing +2.51%, Wheat falling -2.05%, Cotton down -2.06%, while Sugar and Corn finished the week unchanged.
*Day Trading**
Last week’s trading conditions were extremely slow considering that we had an FOMC meeting on Tuesday and Unemployment on Friday. Usually one of these events — not to mention two in the same week - will drive the market in one direction, but neither really had much of an effect. The choppy trading conditions made it difficult for most day trading systems to turn a profit for the week.
A select few systems were able to profit for the week. Leading the way was Electric Daybreaker II eRL, which traded twice for profits of +$440. Helix ES- which has a knack for profiting in sideways conditions- made +$327.50 per ES. Compass SP had an even number of winners and losers last week, but came out on top by +$130.77 on two trades. Bounce eMD traded once for a small profit of +$40.
Others systems merely treaded water for the week. Electric Daybreaker II ES traded twice for a small loss of -$10 per contract. Bounce eRL traded alongside the eMD, but lost -$50. Daybreaker SP traded twice for a loss of -$75. Electric Daybreaker II NQ had one losing short trade from Friday for a setback of -$90.
R-Mesa eRL had a pair of trades that yielded a loss of -$120 per contract. Impetus eRL had similar results losing -$150 per contract on two trades, while R-Mesa SP traded on Wednesday and Thursday (two trades on Thurs) for a total loss of -$325. Clipper eRL traded a handful of times last week for losses amounting to -$620 per contract. RC Miracles ES and RC Success ES were down -$630 and -$1,127.50 by the end of the week.
**Swing Trading**
Most swing trading systems live by the theme: “the trend is your friend (at least the short term trend)†and after an exciting moth in October, November started out promising much more of the same as some nice short term trends have developed. .
Stock index markets rocketed higher last week after finishing October lower. The move higher took a majority of swing systems along for the ride. The trade of the week goes to Axiom eMD, which reversed long a week ago Friday and continues to hold long for open trade profits of +$2564.10. Not far behind is Eclipse eRL, which is also holding long from October 28th with open trade profits of +$2,456.10.
For those of you who like to see gains like those locked in a little more quickly, you should be looking into the Delphi systems. Delphi eMD entered within a few hours of Axiom eMD; however is now out of the market with locked in gains of +$1,990. Delphi exited the position on a profit target Wednesday.
In a similar display of trading Axiom eRL and Delphi both entered long last week and are holding onto open trade gains of +$1,590.60 and $1,540 respectively…the question is when will either system be locking in some profits? Assuming neither system hits a profit target Delphi eRL stands to make approximately $360 more per contract based on today’s close.
In other excitement, the Seasonal ST system by Theseus had the most impressive ES trade of the week. The system entered long on Monday morning and closed out its long on Friday’s close for again of +$1,032.50 per contract. Not to be outdone was AG Mechawarrior ES which closed out a profitable trade Monday and Wednesday for gains of +$877.50 on the two trades.
Other index market trading included open trade gains of +1,262.50 by Axiom ES, open and closed trade gains of +$307 and +$170 by Tzar ES and Tzar eRL, minor gains of +$80 and +$30 for Bounce eRL Swing and Bounce eMD Swing, a small open trade loss of -$280 on a new short position by Tzar NQ, and finally a loss of -$3430 by Tzar eMD on a closed out short position.
Despite last week’s FOMC meeting and subsequent basis point sell off in the bond market, systems were surprisingly quiet, with only Jaws Narrowneck portfolio posting a single trade for a loss of -$893.75. The system is preprogrammed to close out open trades prior to the FED meetings and Unemployment days (last Friday) in anticipation of unpredictable market conditions around each announcement.
Finally, in energy market trading Axiom CL 135 locked in a gain of +$250 on a short trade while Axiom CL is still holding short from $60.30. This is the systems second attempt at capitalizing on the recent down trend in the Crude market…the position is looking good with Crude down -$1.11 today.
**Long Term**
As we mentioned last week in this section, short US Treasury positions are popular amongst long term, trend following systems as bonds have been trading steadily lower since September 1st. And with the Federal Reserve showing no signs of halting the ¼ point rate hikes any time soon - bonds could continue on their downward trend for the foreseeable future.
For long term trend followers, the continued rate hikes may be just what the doctor ordered. Trend following systems have had very few market trends to follow in ’05 and predictably everyone from the small system trader to billion dollar CTAs have struggled with the trend following investment strategy. But thanks the US Government (and your neighbors Interest Only Mortgage) rising interest rates have led to a huge downward trend in the bond markets that has not only seen bond prices fall in the US, but also fall in Europe, Asia, and Australia as well. Leading to an abundance of downward trends for both system traders and CTA’s to capitalize on.
So, if your mortgage rates are rising on your ARM, here’s hoping that you are at least invested in several long term systems that are taking full advantage of the current rate environment. Systems with short positions include Andromeda which is short in the 30 year bonds for gains of +$1887.50 per contract, short in the 10 year notes for profits of +$1200.00 per contract, short in the 5 year notes for profits of +$812.50 per contract, and short in the Eurobund for profits of +$1210.00 Euro per contract.
Aberration Plus also has its fair share of open short bond positions with for profits of +$418.75 per contract in the 5 year notes, +$293.75 per contract in the 2 year notes, +$1250.00 per contract in the Aussie 10 year, +$675.00 per contract in the Eurodollar, and +$160.00 per contract in the Eurobund.
Axiom LT has also benefited with open short positions in the 10 year notes for gains of +$2778.12 per contract, in the Eurobund for profits +$1267.00 per contract, and the Swiss Government Bond for profits of $1042.26 per contract.
Other systems with short positions include Brix which is short in the Ten Year notes for gains of +$1153.00 per contract and in the Eurobund for gains of +1318.80 per contract. SEMA 4 Symmetry is short in the 5 year notes for profits of +$231.25 per contract.
Please Login to: http://www.attainaccess.com for the latest updated statistics.
IMPORTANT RISK DISCLOSURE
Futures based investments are often complex and can
carry the risk of substantial losses. They are intended for sophisticated investors and are not suitable for
everyone. The ability to withstand losses and to adhere to a particular trading program in spite of trading
losses are material points which can adversely affect investor returns.