Backtesting for the Optimum HBPP Allocations

General Discussion on the Permanent Portfolio Strategy

Moderator: Global Moderator

User avatar
sophie
Executive Member
Executive Member
Posts: 1959
Joined: Mon Apr 23, 2012 7:15 pm

Re: Backtesting for the Optimum HBPP Allocations

Post by sophie » Thu Aug 15, 2019 7:26 am

Interesting question & reporting - thanks guys!

Applying what I know about statistical analysis to this question...I think you'd have run a permutation test, also known as a bootstrap. I would do this: Take each year's gain and average it with the year before and year after (since a given year's performance is not independent of adjacent years). Randomly shuffle each year since 1972 (or 1974 if you're afraid of the artificial gold spikes in 1972-73), then string together the first 15 years that come up to produce your outcome statistics. Do this several hundred times, or as long as it takes to get a stable distribution. Hope one of you has some time to do this ? (Sadly I don't.)

Going further than that, I'd label each year according to the economic condition represented i.e. prosperity, deflation, inflation, recession. Make sure each of these is represented in the random sample according to historical distributions.

You'd then have to run this for each combination of asset %'s to determine the optimal set. I believe this is what HB did at some point, which is how he arrived at the 25x4 percentages. I'm not sure if he balanced the economic conditions though, so he may have overweighted inflation & recession. That's why the Golden Butterfly is an interesting variation, to me: it recognizes that prosperity has dominated long enough that is not an unreasonable expectation that it will continue to do so going forward.
Kbg
Executive Member
Executive Member
Posts: 2815
Joined: Fri May 23, 2014 4:18 pm

Re: Backtesting for the Optimum HBPP Allocations

Post by Kbg » Thu Aug 15, 2019 10:23 am

For me I’ve long thought the actual secret sauce of the PP is the premise that we can not predict...ergo a lot of fancy statistical analysis flies in the face of the premise. We do have history and there we have to make an assumption that future will resemble past.

Good moment for full disclosure...to really properly have done the analysis for risk parity I would have ran the to date st dev each year and tweaked port%s slightly.

25% each is near zero predictive...but back to history, asset to Econ condition was based on historicals.

My backtest assumed the same assets PP came up with and that long term volatility was a tad more “neutral” given some assets have more jet fuel than others.
User avatar
vnatale
Executive Member
Executive Member
Posts: 9423
Joined: Fri Apr 12, 2019 8:56 pm
Location: Massachusetts
Contact:

Re: Backtesting for the Optimum HBPP Allocations

Post by vnatale » Mon Jan 27, 2020 12:10 pm

Tyler wrote:
Tue Sep 25, 2018 8:10 pm
Nice article. Thanks! It's always nice to see people talking about the variety of simple asset allocations available and sharing Harry Browne's ideas.

Now if we can just get these financial guys to stop using single arbitrary start dates to draw definitive conclusions about portfolios. I think a major draw of the PP is not the returns alone but how incredibly consistent it was no matter what timefreame you sample. They start to get there with the Sortino talk, but IMHO it goes deeper than that. The PP is simply an extremely dependable portfolio.
Tyler,

I know you are a person of great humility so it's not easy for you to praise yourself.

But am I correct to assume that all the work you have done at your web site subsequent to the start of this Topic now supersedes just about all the information in the prior posts here?

In other words, you've come up with better, more refined models which use better information?

That'd be my best guess!

But I'm also almost certain you'll downplay what you've accomplished.

Vinny
Above provided by: Vinny, who always says: "I only regret that I have but one lap to give to my cats." AND "I'm a more-is-more person."
User avatar
Tyler
Executive Member
Executive Member
Posts: 2066
Joined: Sat Nov 12, 2011 3:23 pm
Contact:

Re: Backtesting for the Optimum HBPP Allocations

Post by Tyler » Mon Jan 27, 2020 12:27 pm

vnatale wrote:
Mon Jan 27, 2020 12:10 pm

But am I correct to assume that all the work you have done at your web site subsequent to the start of this Topic now supersedes just about all the information in the prior posts here?

In other words, you've come up with better, more refined models which use better information?

That'd be my best guess!
There are lots of smart people on this forum, and I wouldn't claim that anything on PC automatically supercedes the opinions of anyone other than myself. But I've spent countless hours over the years improving the quality of my data and tools, and my analysis skills have definitely gotten more sophisticated over time. One of the perks of constantly reminding yourself to stay humble is that you never get so over-confident that you shut yourself off to new information. So I continue to learn new things over time and am happy to share.
Prakh
Junior Member
Junior Member
Posts: 1
Joined: Thu Aug 06, 2020 6:46 am

Re: Backtesting for the Optimum HBPP Allocations

Post by Prakh » Thu Aug 06, 2020 6:47 am

[spam content removed]
User avatar
Kriegsspiel
Executive Member
Executive Member
Posts: 4052
Joined: Sun Sep 16, 2012 5:28 pm

Re: Backtesting for the Optimum HBPP Allocations

Post by Kriegsspiel » Thu Aug 06, 2020 6:52 am

Prakh wrote:
Thu Aug 06, 2020 6:47 am
[spam content removed]
Ahhh, it was kind of nice with the new member's email thing being turned off.
You there, Ephialtes. May you live forever.
Post Reply