The holy grail of trading system design is the perfectly smooth equity curve.
Only the equity curve provides a complete and continuous picture of your system’s performance over time. The usual test summary tells you little about how your design trade-offs alter performance on a day-to-day basis. Hence your system development is not complete until you understand the impact of your decisions on the evolution of account equity.
In this chapter we take a detailed look at how to measure the smoothness of the equity curve using the standard error (SE) from linear regression analysis—the larger the SE, the rougher the equity curve. Then we see how the equity curve for the 65sma-3cc system changes with different exit strategies at the contract level. You will get a feel for how your design choices translate into equity changes.
Next, we discover how SE changes when you combine two systems trading the same market. A common belief is that trading many different markets gives a smoother equity curve. We explore this belief by combining two markets that have some positive covariance.
We then explore the monthly changes in equity curves, examining the performance of the 65sma-3cc system trading the deutsche mark over monthly intervals of different lengths. These quantities are termed the interval equity changes. Our goal here is to see how a system ...