Category: Backtest

Diversification comes in various forms

Maintaining a well diversified portfolio is a time-tested way to protect against going all-in on what turns out to be a terrible investment.  Diversification can also be employed at the strategy level for the same reason.  An example of this is the core-satellite framework, where a rebalanced core portfolio is mixed with different strategies that focus on Relative Strength and Moving Average trend following etc.

It is also possible to diversify across different versions of a single strategy, to reduce the risk of parameter choice misfortune.  For example, rather than relying solely on 12-month returns, for instance, the backtest below equal weights 4 variants of the same model: a 6-month version, 8-month, 10-month and one using 12-month returns all on the same ETFs: EFA, IEF and VTI (the constituents of BNCH).

 

click image for full size version

Just as a well diversified portfolio means that at least some part of it will always be a drag, a composite made up of different model variants will always underperform the best version of the strategy....but it also avoids being exclusively in the worst.

Comparing 2 Ultra-Simple ETF Backtests Side By Side

 The example below is pretty self-explanatory but in a nutshell it compares 2 strategies set side by side in detached browser windows. 

Strategy A on left uses 2 pieces:   1.  50% choose 1 of 3 ETFs using 11-month total return  2.  other 50% using 6-month returns on the same portfolio of ETFs, also choose 1...

Strategy B on right using 1 strategy:  using ONLY 11-month returns.

Rather than only highlight just the overall total return of each,  of high importance is looking at the year by year (Calendar) returns vs a benchmark.   The 100% 11-month strategy has seen years of large outperformance and underperformance.   The blended strategy would have been much easier to stick by and actually achieve the end result - in addition it added return over the period.    We know from many research papers that 3 - 12 month relative strength all have some level of validity long-term.   No matter what the very long-term backtest looks like for these 2 strategies, we cannot know for sure which one is going to do better over the next 10 years.   But we can glean information by studying different types of backtests and help make a judgment about what is happening now.    Indeed, backtests primary function is to help guide you to understand what is happening in the most recent (current) period. 

 

 

Video: Practical Starter Improvements Upon Absolute Return / Cash Filter Strategies

A ~5 minute video using the Regime Relative Strength Backtest to look at some parts of an Absolute Return strategy and ways to improve upon it.

 

to expand, click the '4 expanding arrows' icon in the bottom right corner of the video screen

Short-Sell Backtesting with ETFs

 If you would like to test Short-Selling on ETFreplay, use the versatile app called Rel Str - Combine Portfolios.

You can test going short the top or bottom ranking securities in a list.

Adding Rotation Options For Backtesting ETFs

We have added a new backtest rotation option, which we think delivers some useful flexibility.

Previously Relative Strength strategies could be rotated quarterly, monthly or semi-monthly. Now you can choose a different schedule in the 'Relative Strength - Combine Portfolios' backtest module utilizing a useful feature we call Skip Rotation:

 

 

 

This way you can set for example a 3-month (quarterly) or a semi-annual rotation but not necessarily on CALENDAR quarter ends. So for example, you could offset a quarterly rotation by 1 month and choose Jan, Apr, Jul, Oct. Or you could choose 'every other month' such as in the example below:

 

 

Then below we reverse it so now it skips the opposite months as the above example and instead test an earlier 7-year period:

 

 

Separately, we can actually use this same structure to do some basic seasonality testing. In the test below, we test going long Small and Midcap stocks for the period November to April and then invest simply in the benchmark S&P-500 from May to the end of October. We do this by using checkmarks to move to the cash security (set to SPY) for May, June, July, Aug, Sep and Oct:

 

 

The green question mark icon next to 'Skip Rotation' will, when clicked, produce a pop-up help note with more information about the function. However,  if you have any further questions, please contact us

123