Learn To STOP Curve Fitting!
Download this free guide on how to stop curve fitting. Following these four simple steps can improve your trading dramatically!
In a previous article I took a look at an indicator called the Laguerre RSI. The Laguerre RSI (LRSI) was authored by John Ehlers. You can read about the Laguerre filter in his article, “Time Warp – Without Space Travel“. Within the previous article I was comparing the LRSI to the standard RSI. I did this by creating a simple mean reverting trading model for the E-mini market. During that test, signals were generated by the Larguerre RSI when the indicator value fell below a critical threshold (.10) as you can see in the image below.
This got me wondering what changes the entry trigger might do. For example, what would happen if we waited to open a new trade when the LRSI indicator rises above the lower threshold as in the image below?
So, let’s take a look at how this strategy performs based upon these two types of entries. First, let’s take a look at the testing environment.
Before getting into the details of the results, let me say this: Unless otherwise stated, all the tests within this article are going to use the following assumptions:
This is our baseline and it’s the trigger method I used in the previous article. A trade is opened when the value of the LRSI indicator falls below our lower threshold and is closed when the value of the indicator rises above the upper threshold.
In this case we wait to open a trade when the value of the LRSI indicator rises ABOVE our lower threshold. This means the value of the indicator must first fall below our lower threshold and then rise above it. The concept behind this type of entry is we want to see the falling price of our market recover slightly before opening a new trade. This might prevent us from entering too soon in a falling market. Let’s see how it does.
Looks like this significantly reduces the performance of the trading model. There was virtually no change in max drawdown. No overall improvement here. What does this mean? I think this study is telling us it pays to get in early during a pullback. At least, as defined by our current entry/exit rules. Don’t wait for confirmation of price recovery, instead jump in.
Let’s try something completely different. The studies we have been looking at with LRSI have been based around the concept of mean reverting. That is, we buy pullbacks in hopes that price will soon bounce back giving us a nice profit. I’ve demonstrated in many articles about the mean reversion characteristic of the US stock index markets. However, I think it would be worth testing again with this indicator.
So, in this next test let’s switch up the entry and exit rules. Let’s enter when price crosses above the upper threshold and exit when price crosses below the lower threshold. What we are doing is entering on bullish activity and exiting on bearish activity. In short, we are creating a momentum-based model.
Wow! A significant reduction in profitability. This doesn’t come unexpected. What this study demonstrates again is the mean reverting characteristics of the US stock index markets. Clearly buying into short-term strength is not a strategy worth pursuing. At least, with this type of trading model.
Let’s go back to looking at our mean reverting trading model. In this test let’s enter our trade as soon as the indicator falls below our lower threshold as before. We will change the exit to occur when the indicator falls below the upper threshold. This is different then the previous exit which was to exit as soon as the indicator value rose above the upper threshold. In this case the indicator must rise above the upper threshold and then fall below the upper threshold to trigger an exit. The concept here is to hold during the market snapback and only exit once some type of market weakness is measured by our indicator. This might produce more profit by holding some trades longer.
It looks like this exit paid off. We are making more net profit and this is done with making more profit per trade. Notice we have about the same amount of trades but we have increased the efficiency of our trades by holding them longer. Drawdown is about the same. This looks like a significant improvement to me.
Let’s test another exit. In many of the RSI-based trading models tested on this website, a 5-period simple moving average is used to exit trades. Let’s do that here. We’ll exit when price closes above its 5-day simple moving average.
This produces interesting results. We make about the same amount of profit however, there are many more trades. This trading model also has a slightly higher win great. Drawdown is also slightly reduced.
So, which exit is better? The simple moving average exit (Type 4) or the LRSI exit (Type 5)? I think this depends upon your trading style. If you prefer to have a high number of trades I think the Type 5 model would be for you. If you prefer fewer trades but making each of those trades a bigger winner then the Type 5 model is for you.
Jeff is the founder of System Trader Success – a website and mission to empowering the retail trader with the proper knowledge and tools to become a profitable trader the world of quantitative/automated trading.
Please log in again. The login page will open in a new window. After logging in you can close it and return to this page.