Several readers asked for additional tests to be done on the strategy on Sector trading using the 200-day moving average. We will be testing allocated 11% per ETF instead of 10%, using asymmetric number of days and adding IEF to the SPY MA200 10 day test.
A user commented on ETF Sector Rotation post about a simple idea for trading the sector ETFs, which I can’t believe I have never tried. I like keeping things simple just like my Brazilian Jiu-Jitsu game.
Continuing from the last post, I will show how using different definitions of passing our out-of-sample test can change our results. How luck can play a role if you use only one strategy to test out-of-sample. How you split your in-sample(IS) and out-of-sample(OOS) can change results.
I am frequently asked if I do out-of-sample testing. The short answer is not always and when I do, it is not how most people do the test. There are lots of considerations and pitfalls to avoid when doing out-of-sample testing. Out-of-sample testing is not the panacea it is made out to be. There are lots of grey areas which I will discuss below.
As long time readers of my blog know, I often use a market timing indicator in my strategies. My favorite one, and a simple one, is using the 200 day moving average on either the SPY or S&P 500 Index. I recently ran into these posts, Using Market Breadth To Gauge Market Health (Part 5) and Matt’s Breadth Indicator. Matt’s Breadth Indicator (MBI) intrigued me because I had not seen something like this and conceptually it is simple. I also liked that it was not “easy” to test or optimize on. Therefore hopefully not many people would be using this indicator and I could potentially find better values.
In Simple ConnorsRSI Strategy on S&P500 Stocks I showed a ConnorsRSI strategy on S&P500 stocks. In ConnorsRSI Strategy: Optimization Selection, I narrowed down the optimization to three potential variations that one could consider trading. This post will explore Sensitivity Analysis (also known as: Parameter Sensitivity) to help guide us on what to expect from each variation.
In the previous post, Simple ConnorsRSI Strategy on S&P500 Stocks, I showed a simple strategy which I optimized which gave 1,300 variations. Today, I will cover various methods to choose a strategy to potentially trade.
While doing the research for the next article based on Simple ConnorsRSI Strategy on S&P500 Stocks, I discovered that I had not tested what I wanted. Unfortunately errors are made while doing research and my goal is to catch them before publishing them. I did not in this case. Fortunately the results did not significantly change. The top CAR went from 27.32 to 26.63. As usual the error made the numbers comes down. Why is it that it never happens that they go up? See the post for the corrected numbers. I have also uploaded a new corrected spreadsheet.
Good Quant Trading,
A frequently asked question is how I pick which variation from an optimization run to trade. This post will cover a ConnorsRSI strategy on S&P500 stocks. We will use a wide range of parameters to give us lots of choices to be used in the next post. In that next post, I will show how I take the results and narrow them down to one potential variation to trade. And then the final post, I will cover parameter sensitivity to help determine if the results are likely overfitted or not.
3/27/2017 CORRECTION: When I originally posted this, the results shown in the tables were not for the rules shown below. The table results are now matching the rules as below. The spreadsheet also has the corrected results.
My last post on Country ETF Rotation generated several ideas of what to test to improve the results. See the original post for the list ETFs being traded. One important test I left out from the original post was a baseline case. An idea applied to all the tests was trading more ETFS. For all tests, I will be showing results of trading (2,5,8) ETFs in the spreadsheet. Testing is from 1/1/2007 to 12/31/2016.
