This chart was produced by applying the CTT strategy to historical data, which is something easily done with a computer and some charting software.  I use TradeStation, which is one of the more popular platforms for charting and analyzing market data.  It allows you to put your trading concept into computer code (Easy Language in the case of TradeStation) and apply it to historical market data to see if your idea works, and if it does how much profit it would make.  It also allows one to tune the strategy to optimize its performance.  This can easily lead to over estimating how well the strategy will work when put into actual practice.  In extreme cases, it's possible to "datamine" the historical record to produce a winning strategy based on a completely meaningless concept.  Anyone considering trading futures based on a purchased strategy should be aware that there is a high probability that the strategy will not work as well in the future as it has worked in the past.  

One particular issue with the TradeStation strategy reports is that every time the futures contract rolls over (4 times per year) the historical market data has to be "adjusted" to make it agree with the data for the current contract.  As a result, the TradeStation Strategy Performance reports will not reproduce the same exact numbers once the futures roll over to a new contract and the historical data is recalculated.  This may not be true for every type of strategy, but it is true for CTT.  The further back you go, the less reliable are the numbers, but of course, the further back you go, the less relevant is the data.  I only include it to show that the basic concept persists over a long period of time.