July 2026
IN THIS ISSUE
A probabilistic survey
Why Likely?
I remember well, back in 2019, spending (way too much) time strategizing about what I would name this company. Like every owner, I wanted something that would convey the right messaging to new clients. Something that captured my values and management strategies. Something that distinguished my company from others. Something that piqued curiosities and attracted the right kind of attention.
Oak trees. Greek gods. Castles. Stones.
Solid, safe, but all too mundane in the industry. How to differentiate myself?
Perhaps my most obvious differentiator would be being honest and open about uncertainty. Financial media is full of (over)confident prognosticators acting as if they know what markets will do next. Correctly call a major stock move, remind everyone ad nauseum of that one time you were right, and watch the capital flow in (nevermind all the other incorrect calls of course).
I simply have no interest in playing that game, and naming my company to project this industry-standard (over)confidence felt wrong.
I thought about all my undergrad and graduate math coursework in statistics, probability, and data analysis. Courses where mathematics diverged from rote, determinative calculations and became more about problems that require making assumptions to morph uncertain problems into calculable ones.
Something with managing uncertainty. Probabilistic thinking.
“Thinking in Likelihoods”? I liked it. Projecting uncertainty is definitely not common among investment managers, but that was true to how I thought about and managed money.
A few thoughtful authors also planted seeds in me that further reinforced the “Thinking in Likelihoods” frame:
Annie Duke’s Thinking in Bets: Making Smarter Decisions When You Don’t Have All the Facts.
Resulting refers to judging a decision by its result rather than its process. Drunk driving is a bad decision that could end well (arrive safely). Sober driving is a good decision that could end badly (car accident).
Resulting leads money managers to take credit for profitable trades and deflect responsibility for losing trades, hindering effective reflection and decision making.
When we think of beliefs in binary terms, as in being 100% right or 100% wrong, changing our minds becomes almost impossible. When confronted with mitigating counterevidence we must either make a complete change in our position or make no change at all. Admitting we were wrong is so difficult, so we resist admitting we were wrong, we do not change our beliefs despite the counterevidence, and we carry on making inferior decisions as a result.
The solution, then, is to think and reason along a continuum of confidence levels. For example, saying “I am 60% confident of this” rather than “This is true” helps break out of that binary mindset. When we frame our beliefs as probabilities along a continuum, it becomes easier to recalibrate incremental probabilities rather than make a massive change. Duke recalibrated her play at the poker table by varying bet sizes; the concept applies just-the-same to investment managers.
Nate Silver’s The Signal and the Noise: Why Most Predictions Fail - but Some Don’t.
More data alone does not produce better decision making. Particularly in the age of online content creators and 24/7 news cycles, a reliable process for filtering and understanding the troves of content at our fingertips becomes even more important. And money managers today have a ton of market data at our fingertips.
Good decision makers employ Bayesian thinking to update probabilities incrementally rather than thinking in static binary outcomes.
Overfitting past noise lacks predictive value. For example, day traders make decisions based on short-term gyrations in market prices, and it shows in their long-term performance.
Michael Mauboussin’s The Success Equation: Untangling Skill and Luck in Business, Sports, and Investing.
In uncertain environments, how we parse luck from skill matters. Chess is pure skill, lotteries are pure luck, and investing is somewhere in the middle.
How much we can learn from past outcomes, and how large of a sample size we need to evaluate skill, depends on where the activity falls on this luck-skill continuum.
Mean reversion helps to distinguish high skill from high luck activities. High luck activities see exceptional performers more quickly revert to the mean, whereas high skill activities see greater persistence in outperformance without mean reversion.
It was settled then, I would frame my management around Thinking in Likelihoods. “Likely Capital Management” worked, and the deliberately mis-spelled “Thinking in Likelyhoods” linked the name to the frame.
Now I had to develop a logo. I thought about using probabilistic imagery, such as graphical distributions or mathematical notations, but none of that seemed intuitively recognizable to non-mathematicians. Probabilistically, the Law of Large Numbers guarantees that as sample sizes increase, sample means will converge to expected values - I wanted a logo that somehow captured the concept that anything can happen in the short run, but a good investment process will compound outperformance in the long run.
I have always been awed by the Golden Gate Bridge. Deceptive in size from afar, transporting travelers to their ending destination, rising above turbulent waters, built with solid footers and informed engineering. I also found the experience relatable by which travelers would first drive onto the bridge, perhaps with uncertainty about what to expect, but by remaining diligent and staying in their lanes they would become more and more comfortable with the bridge’s performance as they traversed it. Then looking back from the other side, everything about the bridge just seems so obvious afterward, despite not having that degree of clarity when first driving onto the bridge.
I liked that. So the logo became a Golden Gate-like bridge, but I made a gradient streak starting as a lighter green at the beginning and becoming more solidly green along the bridgeway, just like I envisioned my performance with investors’ capital:
There you have it - why I named this company Likely Capital Management, why the logo is a bridge with a green streak, and why I keep misspelling the name of this newsletter.
ONE MORE THING…
A probability survey. From Team Mauboussin, this survey of probabilistic words shows just how, err, subjective that probabilistic terms can be. Be sure to click on the “Humans vs AI” tab for additional insights on how humans differ from LLMs in their interpretations of probabilistic terms. https://www.probabilitysurvey.com/survey/results
The information and opinions contained in this newsletter are for background and informational/educational purposes only. The information herein is not personalized investment advice nor an investment recommendation on the part of Likely Capital Management, LLC (“Likely Capital”). No portion of the commentary included herein is to be construed as an offer or a solicitation to effect any transaction in securities. No representation, warranty, or undertaking, express or implied, is given as to the accuracy or completeness of the information or opinions contained herein, and no liability is accepted as to the accuracy or completeness of any such information or opinions.
Past performance is not indicative of future performance. There can be no assurance that any investment described herein will replicate its past performance or achieve its current objectives.
Copyright in this newsletter is owned by Likely Capital unless otherwise indicated. The unauthorized use of any material herein may violate numerous statutes, regulations and laws, including, but not limited to, copyright or trademark laws.
Any third-party web sites (“Linked Sites”) or services linked to by this newsletter are not under our control, and therefore we take no responsibility for the Linked Site’s content. The inclusion of any Linked Site does not imply endorsement by Likely Capital of the Linked Site. Use of any such Linked Site is at the user’s own risk.