Buying Wholesale -- Trading Concepts Quantified With ETF Backtesting

A video to demonstrate mean-regression on and some concepts on trading -- for example, many small gains cumulatively add up over time when you buy at wholesale and sell at retail prices.

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

Mean Regression and ETF portfolio backtesting

A video to demonstrate mean-regression on and some concepts related specifically to ETF mean-regression.


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

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.

Strategy Diversification: Combine a core allocation with regime based portfolio switching

Back in 2010 we created our first multiple strategy module, the Advanced Relative Strength backtest, allowing subscribers to combine together different models into an overall portfolio.  To illustrate the backtest, we produced a simple example that employed two sub-strategies; a basic US equity model (MDY, IWM, SPY and QQQ) and an international model using smaller developed country funds (EWA, EWC, EWH and EWS).

The example below uses the same ETFs as that original illustration, but this time, rather than running each model concurrently, we have employed the SPY / EFA ratio moving average as a regime switch to dynamically alternate between the two portfolios.  When the SPY / EFA ratio is trending upwards (i.e. above its MA), the backtest invests in the US equity portfolio.  When the opposite is true, it switches to the International stock portfolio.  This regime approach is then mixed with a solid fixed income core portfolio (IEF and LQD) to form an annually rebalanced 60-40 strategy.



The Core-Regime Portfolios backtest is available to pro subscription members.

Regime Change Backtest Example

Regime Change is used in finance to describe when a condition changes.   IF [condition1] is met,  THEN invest in [X]...   ELSE invest in [Y].   ETFs allow us to easily test conditions which are defined not by some calculation you've created to simulate an index,  these are publicly traded securities with real money invested in them.  There is no ambiguity as to the rules when you use real-world securities as is so often the case with non-financial regime tests.  

Here is a simple example to get the hang of it, is the NASDAQ-100 going up?  If it is, buy it.  If it isn't, invest in a different type of ETF.   In this example, the different type of ETF is defined by the QUALITY FACTOR.   Quality stocks are those with strong balance sheets, lower earnings variability & higher Return On Equity -- as ranked by indexing firm MSCI.   QUAL actually owned real stocks on each day with real money, we aren't subjectively now determining what should be classified as quality and what shouldn't.

What does the performance report look like for this idea?  See below for summary version of an backtest report  (statistical analysis excluded in image below).

Then try other ideas.   All of your ideas don't have to work for you to be very successful at this.   Indeed, this strategy has underfperformed its benchmark 46% of the time in last 5 years (as measured by relative performance in each calendar month).  Yet the outperformance over time has been good.