The World’s Longest Trend-Following Backtest

/The World’s Longest Trend-Following Backtest

The World’s Longest Trend-Following Backtest

By | 2017-08-18T16:55:06+00:00 November 9th, 2015|Key Research, Tactical Asset Allocation Research|8 Comments

Were in the middle of an academic research project and we ran a simple long-term trend-following model from January 1, 1801 to September 30, 2015.

Recently, there has been some research on the performance of trend-following rules over long periods here (and highlighted by CXO here).

Our trend-following methodology is further described in our downside protection piece.

  • Absolute Performance Rule: Time Series Momentum Rule (TMOM)
    • Excess return = total return over past 12 months less return of T-Bills
    • If Excess return >0, go long risky assets. Otherwise, go long alternative assets (T-Bills)
    • Concept made popular by Gary Antonacci
  • Trending Performance Rule: Simple Moving Average Rule (MA)
    • Moving Average (12) = average of 12 month prices
    • If Current Price – Moving Average (12) > 0, go long risky assets. Otherwise, go long alternative assets (T-Bills).
    • Concept made popular by Meb Faber
  • Robust Asset Allocation Rule: Combination of TMOM and MA (ROBUST)
    • 50% TMOM, 50% MA

Our study includes 6 asset classes and strategies assessed over the sample time period:

  • SPX = S&P 500 Total Return Index spliced with generic US stock market data in early years
  • LTR= 10-Year Treasury Total Return Index
  • SP_MA = SPX with MA rule applied
  • 60,40=60/40 SPX, LTR
  • SP_TMOM= SPX with TMOM rule applied
  • SP_ROBUST= SPX with ROBUST rule applied

Results are gross, no fees are included. All returns are total returns and include the reinvestment of distributions (e.g., dividends). Indexes are unmanaged, do not reflect management or trading fees, and one cannot invest directly in an index.

Key Trend-Following Results

First, the laundry list of domestic equity drawdowns over time that exceed 15%. I’ve highlighted the worst performer in red across the index, 10-years, and the index with MA:

The World's Longest Trend-Following Backtest_1800-2015 drawdown tables

The results are hypothetical results and are NOT an indicator of future results and do NOT represent returns that any investor actually attained. Indexes are unmanaged, do not reflect management or trading fees, and one cannot invest directly in an index. Additional information regarding the construction of these results is available upon request.

Takeaways

  • MA rule, TMOM rule and ROBUST rule, historically, have reduced drawdowns
  • Treasury bonds, historically, act like insurance assets and serve as a “crisis alpha” instrument

Robustness

Here we look at top SPX drawdowns and the associated results across the different strategies over two sample periods:

Downside Protection: 1800-1926

The World's Longest Trend-Following Backtest_1800-1926

The results are hypothetical results and are NOT an indicator of future results and do NOT represent returns that any investor actually attained. Indexes are unmanaged, do not reflect management or trading fees, and one cannot invest directly in an index. Additional information regarding the construction of these results is available upon request.

Downside Protection: 1927-2015

The World's Longest Trend-Following Backtest_1927-2015

The results are hypothetical results and are NOT an indicator of future results and do NOT represent returns that any investor actually attained. Indexes are unmanaged, do not reflect management or trading fees, and one cannot invest directly in an index. Additional information regarding the construction of these results is available upon request.

Bottom line: asset allocation and tactial market timing are interesting subjects if one seeks to minimize tail risks.


  • The views and opinions expressed herein are those of the author and do not necessarily reflect the views of Alpha Architect, its affiliates or its employees. Our full disclosures are available here. Definitions of common statistics used in our analysis are available here (towards the bottom).
  • Join thousands of other readers and subscribe to our blog.
  • This site provides NO information on our value ETFs or our momentum ETFs. Please refer to this site.

Print Friendly, PDF & Email

About the Author:

After serving as a Captain in the United States Marine Corps, Dr. Gray earned a PhD, and worked as a finance professor at Drexel University. Dr. Gray’s interest in bridging the research gap between academia and industry led him to found Alpha Architect, an asset management that delivers affordable active exposures for tax-sensitive investors. Dr. Gray has published four books and a number of academic articles. Wes is a regular contributor to multiple industry outlets, to include the following: Wall Street Journal, Forbes, ETF.com, and the CFA Institute. Dr. Gray earned an MBA and a PhD in finance from the University of Chicago and graduated magna cum laude with a BS from The Wharton School of the University of Pennsylvania.

8 Comments

  1. John Butters November 10, 2015 at 5:25 am

    Hi Chaps,

    Are you aware of:

    “215 Years of Global Multi-Asset Momentum: 1800-2014”, Christopher C. Geczy & Mikhail Samonov and,

    the purported 900-year multi-asset trend-following backtest in “Trend Following with Managed Futures”, Greyserman & Kaminski?

    Best wishes, John

  2. John Butters November 10, 2015 at 10:10 am

    Oh, and also Lemperiere et al, “Two Centuries of Trend Following” (also multi asset). These guys have an interesting-looking firm.

  3. Marcos Perez November 22, 2015 at 11:48 am

    Great work Wesley, as always, and thank you to share it.

    My problem doing this kind of research by myself is always the lack of historical data. Where one can find such a huge historical data series? I red Winton hires historians and archeologists in order to find ancient data, as for example monthly rice prices in Japan and China centuries ago…

    Thanks again and hi from Spain!

    • Wesley Gray, PhD January 27, 2016 at 9:20 pm

      Global Financial Data is a good place to start

  4. Martin_Schwoerer December 19, 2015 at 6:12 am

    An excellent compliation and analysis of very useful data, thank you very much!
    I added up which of the three momentum strategies were more often effective in reducing drawdown. “Antonacci” won most often (16 of 29 cases); “Faber” won in seven cases; there was a draw in six cases; “Robust” won in zero cases. But this is just a quick-and-dirty count and say nothing about average or median drawdown or its effect on the CAGR.

  5. Rick July 10, 2016 at 4:37 pm

    Hi Wes

    What are your thoughts on calculating time-series momentum as excess return (like you’ve done here, subtracting the t-bill return) vs just as total return (without subtracting the t-bill return)?

    I appears to me that most of the research has been done with total return, though your excess return feels more logical. Would it have made a difference during the high inflation period in the 70s/80s? thanks

    • Wesley Gray, PhD July 11, 2016 at 11:01 am

      don’t think it matters that much to be honest. Out of sample there will be some version of TS-MOM that will be the best (ie 10.56 months in excess of 10yr bond rates)…so the key is to pick a TS-MOM rule that is in the ballpark and STICKING WITH IT.

Comments are closed.