Classical technical indicators like RSI and Stochastic are commonly used to build algorithmic trading strategies. But do these indicators really give you an edge in your market? Are they able to define the times when you want to be invested? This article will show you a way to quantify and compare the edge of technical indicators. Knowing the edge of the indicator makes it an easy task to select the right indicator for your market.
The edge of an indicator
Any technical indicator, let it be RSI, moving averages or jobless claims, has got a primary goal. It should signal if it is a wise idea to be invested or not. If this indicator signal has any value, on the next day the market should have a higher return than it has on average. Otherwise the usage of no indicator and a buy and hold investing approach would be the best solution.
The edge of an indicator in investing consists of two legs.
- the quality of the signal
- the number of occurrences
The quality of the signal can simply be described as the average close-to-close market move after the signal occurred.
Reading an Indicator
To quantify the prognosis quality of a technical indicator we first have to have a short look on how to set up the test. Therefore I introduce a standardised set of rules on how to interpret the indicator. This will it make possible to compare different indicators based on the same rules, thus only testing the quality of the indicator and not the quality of the rules.
As an example, the slow stochastic indicator (and any other indicator) can be described using 2 rules:
- the absolute level of the indicator
- the direction of the indicator
Using these 2 rules to describe the indicator, a possible test could be: If slow stochastic is between 0 and 20 (and rising/falling), should I be invested on the day after?
Annualised Indicator Edge
As mentioned above the edge of an indicator is defined by the quality of the signal and the number of occurrences. Let’s first concentrate on the quality of the signal only.
I like to use annualised readings, so I easily can compare the market returns to the quality of my indicator signals. Therefore the average percentage daily market move after a signal has occurred is multiplied by the number of trading days. This I will call the annualised indicator return.
Stochastic and S&P 500
Using the layout given above we can run a test of the edge of the 9-day slow Stochastic indicator (as an example indicator) using various settings:
The chart above gives you the annualised indicator edge depending on the absolute level of the indicator. The direction of the indicator was not taken into account and could be the basis of another test.
Comparing these results to the average buy&hold return it is clearly visible which levels of stochastic offer an edge in the S&P.
If the 9-day slow stochastic is between 0 and 20, the market has an annualised return of more than 30% on the next day (close to close). As the average annualised market return on any given day is around 10%, an investment in S&P in oversold areas seems to give excess returns.
Performance=Edge*No. of Occurrences
Beside the edge of the signal the number of occurrences is important to measure the quality of an indicator. If your 100% confidence signal only occurred every few years, you most probably will die as a poor man.
Summing up the percentage returns after indicator signals shows a clear correlation between the quality of the signal and the quality of the summed up returns. The setting with the highest edge (0-20) also has got the most favourable return curve. The chart above shows the total % return of the market within the given indicator settings.
Compare technical indicators and markets
Using the calculations given above I ran a short cross market test over 2 indicators: The 9-day RSI and the 9-day Stochastic. Both are tested for the signal quality in the oversold area from 0 to 30. Data from 2000-2019 has been used.
First have a look at the annualised indicator return, defining the quality of the signal. Nasdaq seems to respond best to both indicators, showing the highest annualised return for RSI.
Also the spread between the annualised indicator return and the average market return is important. As it can be seen, all four markets had about the same average yearly buy&hold return since 2000 (5-6%). The spread between the annualised indicator return and the average market return is the key number in this scan. It defines the absolute edge the indicator offers in a specific market for a long only investor. The scan also shows RSI with Nasdaq or S&P as the best combination for buying in the oversold area.
Separating the quality of the indicator signal from the number of occurrences makes it easy to compare technical indicators and settings. Showing the spread between average market returns and the returns after an indicator signal has occurred enables you to find the best indicator-market combinations.
The analysis has been done using the tradesignal software suite.