Practical academic paper related to #100 – Trading WTI/BRENT Spread
"Thorsten Lubnau devotes in  an own page to the data question. But it is just a summary of well known facts like “The financial crisis starting in 2008 led to a sharp decline of oil prices”. The essential question of rolling is not addressed at all. The used time series is shown in figure 1 of the paper (see screen shot after Graphic-5). The figure matches the picture in Graphic-5. They are obviously unadjusted. One can consider the effect of rolling during the course of trading simulation. But everyone with a minimum of quantitative finance experience avoids this nasty and error prone task and uses backadjusted data. Packages like Unfair Advantage from CSI provide this feature automatically. Lubnau does not mention this point in his further considerations. He has ignored the effect of rolling at all.
All indexes start with 1,000,000$. The fixed-date rolling time series (red in Graphic-14) ends with a final value of 821,750$. The max. volume rolling time series (yellow) does in between considerable better, but the final result is with 781,020$ even worse. The different behavior in between is due to good/bad luck. There are large up- and downs. The swings within the Bollinger band are just noise. If the noise hits the band on the right side, the performance jumps up, if it is on the wrong side, the strategy nosedives. The green unadjusted time-series does much better. The final value is 3,019,900$. The overall win is +201,9%. The Sharpe-Ratio is 0.61 and the max. relative drawdown is 42.9%.This is not bad, but it is far from the > 3.0 Sharpe ratio claimed by Th. Lubnau.
Are you looking for more strategies to read about? Check http://quantpedia.com/Screener
Do you want to see performance of trading systems we described? Check http://quantpedia.com/Chart/Performance
Do you want to know more about us? Check http://quantpedia.com/Home/About
Share onLinkedInTwitterFacebookRefer to a friend