Many successful traders share consistent habits, one deeply ingrained habit will be thorough backtesting of their trading strategies. Backtesting your trading strategy can never guarantee profitability, but as with many of the themes we cover as part of our trader education series, backtesting is an essential part of any professional trader’s armoury. In this article we’ll examine some potential biases that can ‘bleed’ into backtesting, we’ll look at how to minimise the impact of these biases. However, let’s start with a background on backtesting, what it is and how it can be used to increase a trader’s probability of success.
Knowing how to, when to and why you should backtest trading strategies is an invaluable skill that all traders should possess. Backtesting is a straightforward procedure which should always be included in the final analysis of any strategy before that strategy is tested in live conditions. Backtesting should be at the core of every strategy and contained in every trading plan. One key (and often overlooked) benefit of back-testing FX strategies is that backtesting results in FX can often be ‘purer’. There is very little ‘feedback loop’ with FX, add this to the fact that the individual size of movement measurement is small (the single pip movements are generally 1% of the currency pair’s price) and it becomes clear at the outset that backtesting and forex have a symmetry and synergy that result in the backtest being far more accurate with forex vis a vis other securities.
Backtesting can be defined as the process of testing a trading strategy on prior time periods. Rather than applying a strategy for the time period forward, which could take years, a trader can do a simulation of their trading strategy on past data to gauge its effectiveness and profitability. Most technical-analysis strategies are tested with this approach. When you backtest a theory, the results achieved are highly dependent on the movements of the tested period. Backtesting a theory assumes that what happens in the past will happen in the future, and this assumption can cause potential risks for the strategy.
Backtesting evaluates a strategy by applying it to historical data. Backtesting can be used in situations when evaluating how a trading method would have performed in past markets. A key element of backtesting, that differentiates it from other forms of historical testing, is that backtesting calculates how a strategy would have performed had it actually been applied in the past. This requires the backtest to replicate the conditions of the time in question in order to get an accurate result.
Backtesting is a common and methodologically accepted approach to research, however a high or successful correlation between a backtested strategy and historical results can never prove a theory correct, since past results do not necessarily indicate future results. Markets are constantly evolving, however, in the FX world, were yesterday’s behaviour may resemble today’s, backtesting is an extremely useful tool of analysis and prediction.
Backtesting can be applied to any set of historical data, but it is most useful were processes lead to the production of measurable data, taken over a long period of time, and are chaotic enough to suggest a statistical approach will prove relevant. In the application of backtesting techniques to capital markets, backtesting is a specific type of historical testing that determines the performance of the strategy if it had been employed during past periods and market conditions. Since backtesting uses real data, it has advantages over testing with synthesised data sets. While backtesting does not allow the user to predict how a strategy will perform under future conditions, its primary benefit lies in illustrating the vulnerabilities of a strategy as it encountered real-world conditions of the past. This enables the designer of a strategy to learn from their mistakes without actually having to make them with actual money. With the advent of electronic trading and more accessible online databases basic backtesting has become an option for casual traders and is often included as part of an investor’s online brokerage account.
Various types of capital market strategies can be backtested as trading strategies. Other types of strategies are less amenable to backtesting, such as programmed trading strategies for buying or selling large quantities of a stock at the best prices by spreading the trade over a period of hours, days or weeks. This is because the act of selling large quantities of an individual issue affects the trading price for that issue, resulting in a feedback loop. Since the feedback loop is the effect being studied, backtesting is inappropriate for such strategies.
There are many problems that can occur when you backtest your trading system, but most problems fall into one of three categories: post-dictive errors, too many variables, or failing to anticipate drastic changes in the market. Let’s examine each of these problems with potential methods of avoiding errors.
Postdicitve error is a euphemism for what’s become to be known in the trading industry as ‘curve fitting’, using information only available “after the fact” to test your methodology, a very common error when testing trading systems. Certain software apps. allow you to use today’s data when testing a trading system, which is always a postdictive error. We don’t know if today’s data is useful for predicting the future, we do know if it’s useful for predicting the past. You may have a system that incorporates the closing price, then this obviously means that the trade cannot be initiated until the day is over, otherwise this is a postdictive error. Another example may help illustrate the postdictive error, if you have a rule in your trading system about highest prices, then you will have a postdictive error. This is because highest prices are often defined by data that comes later, in the future.
The way to avoid the postdictive error is to make sure that when you backtest a system only information that is available in the past, at that point in time, is used in backtesting. With manual backtesting or backtesting most forex testers you can accommodate this quite easily, but with automated backtesting the postdictive error can find its way a trading system.
Variables
Traders often have too many variables, or trading indicators in their trading systems. It’s quite straightforward to create a trading system that can easily translate the past price behaviour of a currency pair. The more indicators you add, the easier the evaluation can be. However, problems can arrive when the system is applied to future predictions. When a trading system contains several indicators it can predict the behaviour of the market during a time period extremely well given the underpinning by mathematical constructs.
Changes in the Market
Many traders forget to anticipate ‘outlier’ events that will occur. There will be times in the future when the markets behave erratically, traders should have designed their trading system to remain functioning during these times. When the global financial crisis started unfolding in September 2008, most currency pairs traded with much more volatility than had been seen for years. How do you prepare for the unexpected? Consider these simple solutions.
Exaggerate your expected losses in your backtest. If your backtesting reveals a maximum loss of €5000, assume a maximum loss of €10,000. Will your trading system still be profitable under these conditions? Decide on an appropriate level of risk for each trade. If you have decided to risk 1% on each trade, you should assume that sometime in the future, you may be in a trade and an unexpected event will occur, and your trade will not lose 1%, but instead 1.5% will be lost. You should have a contingency plan, how to exit a trade if an ‘event’ occurs and you can’t access your account. For example, if your trading platform is inaccessible and you desperately want out of a trade and you don’t have a stop in place.
Set a maximum risk level set. If you risk 1% per trade and you have 7 trades open simultaneously, does this mean that you will be risking 7% of your account? Or have you decided on a maximum risk level of 3%? Keeping in mind that the unexpected will occur, you should probably have a maximum risk level for those times when you have several open trades, perhaps only take three of the set ups.
The maximum drawdown you are willing to tolerate is critical to your success. You are more likely to underestimate the value and overestimate the severity of drawdowns they can withstand. Losing 30% of an account may encourage traders to cease trading temporarily, losing 50% may curtail their career. The most effective strategy to plan for drawdowns is to extensively backtest to find out what level of historical drawdowns the trading system experiences and then plan for the worst drawdowns. Anticipating drastic changes in the markets is the single best way to preserve the equity in your account.
Successful traders backtest their trading strategies. Thorough backtesting separates successful and wealthy traders from the average, or those who lose money. You’ll know several ways of incorporating backtesting into your trading regime once you begin experimentation. You’ll begin to understand the pitfalls (what to look out for) when you’re backtesting, ensuring you can get the most out of the process. Some of the most powerful trading systems available are extremely simple. Keep this in mind as you trade, and as you attempt to find a profitable trading system. Most traders will find that with experience, they become more likely to embrace the view that simpler trading is preferred over a complex approach. However, even the simplest indicator based trading methods can be backtested, a major currency pair crossing S1 or R1 or the 200 ma can be tested. If new to backtesting the simplest backtest, even if not the trader’s main strategy, may be a good starting point.
