Portfolio Charts

Ask your investment, budget, and other money related questions here
FBeyer
Posts: 1069
Joined: Tue Oct 27, 2015 3:25 am

Re: Portfolio Charts

Post by FBeyer »

BRUTE wrote:...brute is always a little irritated when humans tell him not to chase backtesting or rely on historical data. historical data is the only data there is.
Be irritated all you want. Portfolio back testing without a prior hypothesis is a prime example of data dredging. https://en.wikipedia.org/wiki/Data_dredging

So, what was your hypothesis about AMERICAN small cap and emerging markets before you plugged those numbers into portfoliofinder?

There is also the very real issue of extrapolation:
http://stats.stackexchange.com/question ... rapolation

Portfoliofinder is a LOT of fun to fool around with. It gives a lot of pretty pictures and graphs, and it is the most easily misused tool for dredging because is it SO easy to see patterns in the sky that we didn't think of first ourselves. Here be dragons. There is a very real reason why a horde of data scientists and statisticians have dedicated their lives and education to the art of handling, reading, and analyzing data. Numbers are not just numbers, not even when they're very easy to come by.

BRUTE
Posts: 3797
Joined: Sat Dec 26, 2015 5:20 pm

Re: Portfolio Charts

Post by BRUTE »

the hypothesis thing is definitely true. brute did not have anything to say about US small cap.

does (falsely) extrapolating get less likely with bigger datasets? for example, it's certainly (falsely) extrapolated if brute goes all-in on a stock that did well this year. but if a portfolio does well over most of 45 years, brute feels intuitively more certain. is that intuition wrong?

it is really quite tricky to find a fitting portfolio. brute wants his to be mostly passive, and actually values stability. and it might be true that he's engaging in over optimization in the past.

but there are tons of portfolios that do terrible on many accounts even in the past - so wouldn't using one of those be worse than making up one that at least worked in the past? (if it's not extrapolated too crazy, i.e. betting on a very specific stock from a 1 year dataset or so).

for example, while the PP might have been hypothesized before actually looking at the data, it would have historically limited gains pretty strongly. so it would be a case of maybe running into a future problem vs. almost certainly running into the problem the PP has had, always. (of course not applicable if the goal of the portfolio is not to grow, but just to protect existing money - which the PP seems to do).

in another example, 100% TSM would historically have led to 10 year drawdowns multiple times, and even a 13 year drawdown after the 2000 crisis. while that might happen to any of brute's over optimized portfolios, it has already happened several times to the 100% TSM.

the TFP mentioned by FBeyer still had 9 year drawdowns, and didn't do so well in 2008. it did survive 2000 remarkably well, and has been doing well after 2009 though.

point being, it seems like there is no free lunch.

Tyler9000
Posts: 1758
Joined: Fri Jun 01, 2012 11:45 pm

Re: Portfolio Charts

Post by Tyler9000 »

As with most things, the proper approach generally requires a bit of balance.

As I've written elsewhere, relying solely on good backtested numbers with no understanding of why it worked (and may continue to work) is a bad idea. But making decisions based solely on dogma while ignoring history is similarly shortsighted. I like to think of the Portfolios page as helping the first group, and the Calculators as helping the second.
Last edited by Tyler9000 on Mon Dec 12, 2016 6:57 pm, edited 5 times in total.

stayhigh
Posts: 113
Joined: Sun Dec 06, 2015 4:20 pm

Re: Portfolio Charts

Post by stayhigh »

BRUTE wrote:50% Small Cap Value
50% Emerging Markets

discuss.
When you add gold and some bonds it looks very solid.

FBeyer
Posts: 1069
Joined: Tue Oct 27, 2015 3:25 am

Re: Portfolio Charts

Post by FBeyer »

BRUTE wrote: 1) does (falsely) extrapolating get less likely with bigger datasets?

2) for example, it's certainly (falsely) extrapolated if brute goes all-in on a stock that did well this year. but if a portfolio does well over most of 45 years, brute feels intuitively more certain. is that intuition wrong?

3 )brute wants his to be mostly passive, and actually values stability. and it might be true that he's engaging in over optimization in the past.

4) but there are tons of portfolios that do terrible on many accounts even in the past - so wouldn't using one of those be worse...

5) for example, while the PP might have been hypothesized before actually looking at the data, it would have historically limited gains pretty strongly. so it would be a case of maybe running into a future problem vs. almost certainly running into the problem the PP has had, always. (of course not applicable if the goal of the portfolio is not to grow, but just to protect existing money - which the PP seems to do).

6) the TFP mentioned by FBeyer still had 9 year drawdowns, and didn't do so well in 2008. it did survive 2000 remarkably well, and has been doing well after 2009 though.

point being, it seems like there is no free lunch.
I wish we had a white board and a conference room... I don't even know the financials, but the data part alone could take a few hours of lectures. From a data point of view I think these are good questions, I'll do my best to answer to the best of my current knowledge.

1) No. And Yes. :roll:
If 'the process that generates the data' is the same, then more data is better. If the process is different, you need to identify the characteristics of the process to know how to interpret the outcome. Economic conditions change over time, and so the process that generates returns differs over time. Every specific return at some point in time is a result of politics, investor expectations, actual conditions, current momentum and expected stability of returns over time. History shows that unstable times yield more than stable times. Times have been quite stable since the end of the second world war right? Many argue that the post-war buildup has given investors an unrealistic idea of the long term gains of general investments, ie indexing. Go back 70 years and 'things always go up'. Why is that necessarily the case for the next 30-40 years where you and I are supposed to live off of our investments?

Statistical analysis can only give you more information after you applied as much expert knowledge as possible. Math and graphs do nothing on their own, without coupling to domain specific knowledge. It is the most difficult task of the statistical consultant to goad that knowledge from the client before, during and after gathering data. The graphs support the hypothesis. You cannot form a hypothesis based on past data and conclude that you are right, you must conduct a new experiment to see if the hypothesis applies to newly acquired data as well. Pattern recognition is a discipline all on its own, and the alluring thing about pattern recognition is that you seem to get results from data immediately, but what you truly get is 'ideas to test' from past results. It's very hard to explain to people why concluding anything from a past pattern is not a result, but a suggestion. The confusion of the two is the basic pitfall of p-hacking. Expert knowledge on a domain is the pillar on which the data analysis and the pattern recognition rests, not the other way around.

More data means more power. Power means the ability to detect smaller effects/differences. The actual causality of the difference is up the expert to hypothesise on, then back to the statistician who has to help conduct a new experiment to see if the hypothesis is correct. That means that with a lot of historical data, we're quite certain that small cap value stocks HAVE indeed generated a higher return that the total stock market. Why that is is up to someone else to find out. whether that will be the case in the future depends on the underlying mechanism that generated the excess return.

TL;DR extrapolation works when you know you have the same conditions in the domain you're extrapolating to as the domain you're extrapolating from. That is why a higher sampling density on a closed interval gives you better statistics, but analytical forecasting from more data does not. You require expert knowledge of the subject to make efficient use of a forecast.



2) Uncertainty on the mean. By sampling over an index rather than a single stock you're averaging the effect of every single company out and try to capture the compound effect. By analysing more companies over a longer time frame, compared to one company over a short time frame you're simply getting a better estimate of the uncertainty on the mean, or the uncertainty on the CAGR is you will. An investor will most likely want to capture one-tailed outliers, not the average. Your knowledge of the CAGR is better. The improved statistics should give you a much better confidence interval when projecting into the future, yes. That is, if the underlying data generating process is still the exact same... If that is not the case, then the effect from the erroneous data generating model is much more important than the actual accuracy of your parameter estimates from past times. You can extrapolate quite well if you don't extrapolate very far, but you and I are most likely trying to extrapolate 30 years into the future with our lazy portfolios aren't we?

The intuition is not wrong, but rather off. You're more certain that the returns are actual returns, that the numbers are real if you will, rather than flukes of mispricing (fuck the EMH) but the continued realization of those returns in the future depends on point 1) above. The index is more well-priced, almost by definition, than single companies are. Whether the index is correctly priced is something else entirely.

Investments will make money if the fundamentals to make money are there and if the prevalent investor psychology is there to drive prices up. That is the basic issue with fundamental analysis: A vastly underpriced company will not rise in price until the rest of the stock market catches up. Are the fundamentals to keep driving the stock market up at the same pace as in the past there for the next 30 years?

3) If you want stability, why are we talking about a portfolio composed of the two most volatile stock indices? The Permanent Portfolio is designed to be stable. The Global Portfolio is designed to be lazy. Choose one of those instead. There is expert knowledge behind the design of those two, rather than being a back testing driven build.

4) Yes. Do you KNOW and UNDERSTAND why those portfolios fared badly in the past or can you just see that they fared badly by looking at the graphs on portfoliocharts?

5) The PP does exactly what it was designed to do: Preserve capital. It's exact performance based on what it was designed to do is, IMO, one of the reasons why so many people talk about it. This was not a CAGR/efficient frontier optimized portfolio, it had a specific outset and was built from first principles.

6) I pulled numbers out of my ass (PUMA). My point was not to find a portfolio with the smallest drawdowns in the past, that would most likely be the Golden Butterfly, my point was more that your choice of reference ie the TSM was arbitrary. Again, apply knowledge, then dig around in the data, not the other way round.

I know I don't know a lot of things. If I knew things, I wouldn't need to diversify my own investments...

BRUTE
Posts: 3797
Joined: Sat Dec 26, 2015 5:20 pm

Re: Portfolio Charts

Post by BRUTE »

brute thanks FBeyer for the lengthy explanation, even though it just seems to confirm brute's uncertainty.

FBeyer is of course right about the PP, but preserving wealth is currently not brute's goal, creating more wealth is. thus, while brute accepts and likes stability like in the GB, he sees is as more of a bonus - he doesn't have much to lose yet and returns are more important. thus any portfolio that generates great returns while still providing stability would be perfect. this is in essence saying that brute believes there are things too good to be true. in brute's experience, most humans invest for the same reason they do 99% of what they do, to follow the herd. thus it wouldn't be surprising to brute if there is something out there that has both a higher CAGR and shorter drawdown periods. the GB already seems to prove that there is a certain amount of free lunch if not locked into the "stocks/bond - age" dogma.

edit: regarding stability/volatility, brute forgot to mention that he thinks anti-correlated volatile stocks can actually increase stability. kind of a nassim taleb thing maybe, where stability is not the opposite of volatility. it's of course uncertain if assets (or some assets) display these characteristics and will continue to do so. but certain assets seem to have correlated negatively to add up to a pretty stable portfolio, for example the PP and the GB.

User avatar
jennypenny
Posts: 6851
Joined: Sun Jul 03, 2011 2:20 pm

Re: Portfolio Charts

Post by jennypenny »

@brute--There's no reason you have to go all-in on either safety or gains. At first, it's good to focus almost solely on gains. As your portfolio grows, you can take some money out of the 'gains' category and move it into safer investments. It's like how I periodically cash in chips when I gamble to (1) make sure my kitty is always small enough so that a dollar still looks like a dollar (no purple chips!), and (2) I don't give all my winnings back to the house. I've shifted money from stocks to bonds and now to treasuries and gold. After 25 years, the bulk of my portfolio resembles the PP but it was a slow evolution over time into that allocation. And I still have 10% in a trading fund that I will use as an income fund whenever we decide to live off of our kitty.

I'd say have two layers of allocation, the first being a designation of either gains or safety, and then within those another allocation with something like the PP for safety and whatever stock/bond recipe you like for gains.

Sorry if I'm derailing T9000.

ThisDinosaur
Posts: 997
Joined: Fri Jul 17, 2015 9:31 am

Re: Portfolio Charts

Post by ThisDinosaur »

Tyler, what is the nature of your concern about the EM data? Is the earnings data *after* 1985 more trustworthy?

wrt investing Hypotheses, what is the proposed mechanism/reason for the outperformance of Small Cap & International Small Cap indices?

Tyler9000
Posts: 1758
Joined: Fri Jun 01, 2012 11:45 pm

Re: Portfolio Charts

Post by Tyler9000 »

@ThisDinosaur -- The general rule of thumb for how the Simba SS prioritizes data sources is:

1) Known returns from a passive index fund currently traded on the market. It is often the Vanguard version, but sometimes other funds are used if VG is too active in their management.
2) Known returns from the underlying index that the modern fund tracks. This will be directly from sources such as CRSP and MSCI.
3) Reconstructed returns that follow the same methodology as #2 using good source data. For example, I rebuilt the full US stock history from Fama-French data, and another Boglehead did the same for US treasury funds using Federal Reserve data.
4) Other sources.

Long story short -- it turns out that #2-level data for EM starts in 1988 and there's no data available to accomplish #3. We've been using #4 -- a public PDF from DFA -- and recently dug into where those numbers actually come from. It turns out that they simply used 50% int'l value and 50% int'l small as a proxy for EM, but that's really a terrible assumption that does not track known good years even remotely well. So the data prior to mid-80's is getting nixed.

That doesn't mean I'll be removing EM from the calculators. I'm working on something too complicated to explain just yet, but it should be pretty cool once it's done.

WRT small caps, the classical answer is that the market dictates that things with more risk generate greater returns. I'm not sure it's that simple, but it's a good place to start.

Smashter
Posts: 541
Joined: Sat Nov 12, 2016 8:05 am
Location: Midwest USA

Re: Portfolio Charts

Post by Smashter »

I just want to chime in here and say that Portfolio Charts is the best. I am emerging from an all day binge of this thread, as well as related Golden Butterfly threads on Bogleheads and MMM.

Tyler9000 is a freaking saint for always staying classy even when dealing with the most annoying, dense, and rude people the MMM board has to offer. As Brute mentioned, reading through those threads made me appreciate this community all the more.

A quick question for the Golden Butterfly brigade: what would be the best way to organize the GB for tax efficiency? I have a really good 401k and a Roth to work with. Is gold best held in the 401k?

Tyler9000
Posts: 1758
Joined: Fri Jun 01, 2012 11:45 pm

Re: Portfolio Charts

Post by Tyler9000 »

I've learned that patience is an acquired skill that gets easier with practice. That said, getting positive feedback definitely helps along the way. Thanks for the kind words!

Gold is nice in taxable most years because it pays no dividends, but is better in tax deferred when it comes time to sell some to rebalance. Most people like long term bonds in tax deferred. Cash is more tax efficient in tax deferred but way more useful in taxable. And stocks are good wherever.

Personally, I try not to overthink tax optimization in every account. I keep two separate identical portfolios -- one in taxable and one in my IRA. I like my easily accessible (taxable) money to have full portfolio buy-in as that's what I'll be living on for a long time -- we're on ERE, after all. ;) In my experience, the GB (and PP) are already relatively tax-efficient as-is with lots of opportunities for tax loss harvesting thanks to the broad diversification.

BRUTE
Posts: 3797
Joined: Sat Dec 26, 2015 5:20 pm

Re: Portfolio Charts

Post by BRUTE »

Smashter wrote:Portfolio Charts is the best
just historically! no guarantee of future awesomeness.

User avatar
Seppia
Posts: 2016
Joined: Tue Aug 30, 2016 9:34 am
Location: South Florida

Re: Portfolio Charts

Post by Seppia »

Tyler9000 wrote:I've learned that patience is an acquired skill that gets easier with practice. That said, getting positive feedback definitely helps along the way. Thanks for the kind words!
I'm sure that while the critics can be the loudest, there's a very large silent group that really appreciates the work you do, for free, for the benefit of unknown strangers.

Keep being awesome Tyler.

userqname
Posts: 27
Joined: Thu Dec 29, 2016 9:19 am

Re: Portfolio Charts

Post by userqname »

50% REIT
50% LTT

Discuss.

stayhigh
Posts: 113
Joined: Sun Dec 06, 2015 4:20 pm

Re: Portfolio Charts

Post by stayhigh »

userqname wrote:50% REIT
50% LTT

Discuss.
I'd add something else for diversification. Interest rates will play a big part.

Tyler9000
Posts: 1758
Joined: Fri Jun 01, 2012 11:45 pm

Re: Portfolio Charts

Post by Tyler9000 »

Tyler9000 wrote: BTW, I've been working a lot with the guy who maintains the Simba spreadsheet and there's a big update coming. One of the likely changes is that EM may be removed prior to 1985. The more we look into data before that date the less we trust it. Just something to think about.
Tyler9000 wrote: That doesn't mean I'll be removing EM from the calculators. I'm working on something too complicated to explain just yet, but it should be pretty cool once it's done.
If you haven't already noticed, the calculator update is now live and it includes the improved data and also the new system I alluded to above.

https://portfoliocharts.com/2017/01/09/ ... lculators/

Lucky C
Posts: 755
Joined: Sat Apr 16, 2016 6:09 am

Re: Portfolio Charts

Post by Lucky C »

I'm less than two years from my expected FI date and I want to dramatically reduce the risk in my portfolio. The way it is now, if my returns significantly beat expectations maybe I'll retire half a year earlier, but if my returns match some of the worst scenarios historically, that could push me back years! Way more downside than the potential upside for my situation.

I also think it's especially risky to own US stocks and long term bonds right now if you care about short term returns. I want to stick to low-priced international equities and bonds, and only Short Term for US bonds. Throw in some gold and I think I've got some decent diversification.

And so I present this low drawdown FI home stretch portfolio:
25% international bonds - in reality I would do a smaller but riskier combo of EM bonds + LendingClub
25% short term treasury
25% cash
15% international value
10% gold

Returns and Drawdowns

Using the Long Term Returns calculator, over 2 years the upside CAGR is 15% but the downside CAGR is only -3%! Compare to the Permanent Portfolio where the upside CAGR over 2 years is 15% but the downside is -7%. I'm a lot more comfortable with a historical drawdown of about 5% with this portfolio vs. the 13% of the PP to get me to my FI date within a window of a few months - this is more important to me than a percent or two difference in returns over the next couple of years.

As always, past correlations do not guarantee future correlations and all that jazz, but this looks to me like a great way to almost-guarantee meeting my financial goals.

Tyler9000
Posts: 1758
Joined: Fri Jun 01, 2012 11:45 pm

Re: Portfolio Charts

Post by Tyler9000 »

I understand where you're coming from. Having security in your FI date is certainly valuable, and that's extremely impressive from a drawdown perspective. However, keep in mind that your true financial goal is not to reach a specific date with a certain amount of money, but to build a sustainable system you can stick with for the long run. When I was on your position I preferred to start building towards the long-term goal rather than focusing too closely on the next guidepost. Just something to think about.

Lucky C
Posts: 755
Joined: Sat Apr 16, 2016 6:09 am

Re: Portfolio Charts

Post by Lucky C »

My situation is atypical in that I'm looking to get a house that's far away from work this year rather than waiting until FI, for various reasons. This will lock me into a commute that I can deal with for about 1.5 years, or 2 years if the conservative portfolio I describe above turns out to not do so well. If I stick to my current risk level and the markets go south, I'll then be stuck with a hellish commute and not much free time for maybe 4 years instead of <2. To me that would be a nightmare! I'm willingly adding on a couple months of work (based on expected returns) to completely eliminate the risk of a couple extra years of work. Besides, last year my investments and income exceeded expectations, so my predicted end date going the conservative route still makes me very happy - time to lock it down as much as possible!

Also, without getting into an active investing / predicting the future debate, I believe the odds are pretty good that there will be more bargains to buy in 1.5 - 2 years compared to today. I certainly won't regret holding a lot of cash or short term bonds if some prices start to drop, and I'll be comfortable going higher risk again when the time is right. I know that I can successfully manage a riskier portfolio, it's just time for me to take it easy for the short term.

userqname
Posts: 27
Joined: Thu Dec 29, 2016 9:19 am

Re: Portfolio Charts

Post by userqname »

Tyler9000, what Asset Allocation performs best on the Financial Independence calculator? (lowest Maximum time to FI)
I would assume it is the one with the highest perpetual withdrawal rate, and the lowest volatility. Probably resembling the Golden Butterfly.

Also, is there any reason the Portfolio Finder has to cap at 11 assets? It would obviously be preferable to select All Assets and subtract from there.

Post Reply