My trend following strategy and experience

Discuss all general (i.e. non-personal) investing questions and issues, investing news, and theory.
User avatar
Topic Author
willthrill81
Posts: 11032
Joined: Thu Jan 26, 2017 3:17 pm
Location: USA

Re: My trend following strategy and experience

Post by willthrill81 » Thu Jul 11, 2019 9:32 am

BlueEars wrote:
Wed Jul 10, 2019 10:18 am
One testing technique for a backtested strategy is to take the strategy for the longest period that data exists and to split it into two period. Set parameters to optimize the first period. Those are the ones you would have chosen at the end of that period using the results for that period alone. Then look at those parameter's results for the full period. This is often referred to as out-of-sample backtesting.

So perhaps there is 60 years of available data. You take the first 30 years and set any parameters you are using to the best result. Then you use those parameters for the full period of 60 years. Quite often the 60 years results using parameters optimized for the first 30 years will then be not quite as good as the optimization parameters using the full 60 years.

Going forward I think you still want to keep the optimized parameters for the full period of 60 years. But then you are informed in a rough way of how sensitive your results might be going forward. If the better results compared to buy-hold disappear when doing this half period and full period testing, you need to go back to the drawing boards.

Just some thoughts.
Very aptly put. Sensitivity analyses such as these are very useful in many areas of inquiry.
“It's a dangerous business, Frodo, going out your door. You step onto the road, and if you don't keep your feet, there's no knowing where you might be swept off to.” J.R.R. Tolkien,The Lord of the Rings

Forester
Posts: 185
Joined: Sat Jan 19, 2019 2:50 pm
Location: UK

Re: My trend following strategy and experience

Post by Forester » Tue Jul 16, 2019 11:29 am

New article on the method here posted on Allocate Smartly

https://allocatesmartly.com/philosophic ... ing-redux/

User avatar
Topic Author
willthrill81
Posts: 11032
Joined: Thu Jan 26, 2017 3:17 pm
Location: USA

Re: My trend following strategy and experience

Post by willthrill81 » Tue Jul 16, 2019 12:06 pm

Forester wrote:
Tue Jul 16, 2019 11:29 am
New article on the method here posted on Allocate Smartly

https://allocatesmartly.com/philosophic ... ing-redux/
Thanks for the link. They agree with me regarding the main strength of the strategy.
Like most trend-following strategies, the strength of GTT hasn’t been in generating outsized returns; it has been in maintaining returns while managing losses.
emphasis in original

I also find it interesting that they make the following criticism, which the second part of my strategy directly addresses (i.e. rotating into the top performing stock asset class over the prior 7 months).
Where we find GTT lacking is that it’s not really a “total” portfolio solution – it’s a single asset class solution. It would be great to see these same concepts applied to other assets in order to build a more robust, diversified portfolio.
“It's a dangerous business, Frodo, going out your door. You step onto the road, and if you don't keep your feet, there's no knowing where you might be swept off to.” J.R.R. Tolkien,The Lord of the Rings

Always passive
Posts: 382
Joined: Fri Apr 14, 2017 4:25 am
Location: Israel

Re: My trend following strategy and experience

Post by Always passive » Tue Jul 16, 2019 3:00 pm

willthrill81 wrote:
Tue Jul 16, 2019 12:06 pm
Forester wrote:
Tue Jul 16, 2019 11:29 am
New article on the method here posted on Allocate Smartly

https://allocatesmartly.com/philosophic ... ing-redux/
Thanks for the link. They agree with me regarding the main strength of the strategy.
Like most trend-following strategies, the strength of GTT hasn’t been in generating outsized returns; it has been in maintaining returns while managing losses.
emphasis in original

I also find it interesting that they make the following criticism, which the second part of my strategy directly addresses (i.e. rotating into the top performing stock asset class over the prior 7 months).
Where we find GTT lacking is that it’s not really a “total” portfolio solution – it’s a single asset class solution. It would be great to see these same concepts applied to other assets in order to build a more robust, diversified portfolio.
If I recall you do not limit yourself to the S&P 500, but after checking for recession, you select among different indices, including foreign ones. The question is whether one can assume that a US recession will impact the entire investing world?

User avatar
Topic Author
willthrill81
Posts: 11032
Joined: Thu Jan 26, 2017 3:17 pm
Location: USA

Re: My trend following strategy and experience

Post by willthrill81 » Tue Jul 16, 2019 3:12 pm

Always passive wrote:
Tue Jul 16, 2019 3:00 pm
willthrill81 wrote:
Tue Jul 16, 2019 12:06 pm
Forester wrote:
Tue Jul 16, 2019 11:29 am
New article on the method here posted on Allocate Smartly

https://allocatesmartly.com/philosophic ... ing-redux/
Thanks for the link. They agree with me regarding the main strength of the strategy.
Like most trend-following strategies, the strength of GTT hasn’t been in generating outsized returns; it has been in maintaining returns while managing losses.
emphasis in original

I also find it interesting that they make the following criticism, which the second part of my strategy directly addresses (i.e. rotating into the top performing stock asset class over the prior 7 months).
Where we find GTT lacking is that it’s not really a “total” portfolio solution – it’s a single asset class solution. It would be great to see these same concepts applied to other assets in order to build a more robust, diversified portfolio.
If I recall you do not limit yourself to the S&P 500, but after checking for recession, you select among different indices, including foreign ones. The question is whether one can assume that a US recession will impact the entire investing world?
The links in the OP include an analysis of ex-U.S. equities. What might be surprising to some is that, historically, the U.S. unemployment rate has had far more to do with other nations' stock performance than their nation's economic status.
“It's a dangerous business, Frodo, going out your door. You step onto the road, and if you don't keep your feet, there's no knowing where you might be swept off to.” J.R.R. Tolkien,The Lord of the Rings

User avatar
BlueEars
Posts: 3742
Joined: Sat Mar 10, 2007 12:15 am
Location: West Coast

Re: My trend following strategy and experience

Post by BlueEars » Tue Jul 16, 2019 7:25 pm

willthrill81 wrote:
Tue Jul 16, 2019 3:12 pm
...
The links in the OP include an analysis of ex-U.S. equities. What might be surprising to some is that, historically, the U.S. unemployment rate has had far more to do with other nations' stock performance than their nation's economic status.
I would agree from what I have seen.

Some years ago I modified a trend following system as if I were a Japanese using the SP500 as a trend indicator on whether to stay in stocks or go to Treasuries. Also it switched between the EAFE and large US value or large US growth up to 1983 and then the NIkkei (instead of EAFE) was used from 1984 to 2012. This was due to the limits I had on data availability.

The results were converted to Yen too. The CAGR = 15.1% was excellent for such a far sighted :wink: Japanese investor. It did result in a fairly high 2.2 trades per year. I was using this as an out of sample test of the algorithm I was studying.

Post Reply