Position Sizing (Part Four): How We Assess Conviction

This article is authored by MOI Global instructor Sean Stannard-Stockton, president and chief investment officer of Ensemble Capital Management, based in Burlingame, California. Visit Ensemble’s Intrinsic Investing website for additional insights.

This is Part 4 in our series about position sizing. Click on the links to read Part 1, Part 2 and Part 3.

In our last post, we explained why an investor’s conviction in a positive outcome – the probability of success – is just as important as how much potential upside a stock may have when you are trying to determine how much of a stock to own. In this post we’ll explain how we go about ranking the probability of success for companies in our long term oriented investment strategy and how this process drives our position sizing process.

In this post, we laid out a diagram of Ensemble Capital’s investment philosophy. In the diagram, we explained the three core areas we assess and the two key questions we seek to answer in each area.

• Moat
  • How likely is it that the moat be intact in 10 years?
  • How likely is it that customers will value the product/services in 10 years?
• Management
  • Does management understand and execute on creating economic value?
  • Does management thoughtfully weigh dividends, buybacks, M&A, and debt repayment?
• Forecastable
  • Does the business lend itself to accurate forecasting of long-term outcomes?
  • Does our team have the domain knowledge to understand the business?

Each of these questions help us evaluate the degree to which we think we can adequately establish the fair value of a company. We rate each question on a scale of zero to three.

3: We are highly confident in a positive answer to this question. We believe that the odds of our positive answer proving to be correct over time are about 80% or better.

2: We are confident in a positive answer to this question. We believe that the odds of our positive answer proving to be correct over time are about 70% or better.

1: We believe it is more likely than not that a positive answer to this question is correct. We believe that the odds of our positive answer proving to be correct over time are about 60% or better.

0: We are not confident in a positive answer to this question. We think the odds that a positive answer proves to be correct over time are about 50% or worse.

We also assign a “global” conviction rating in which we rate our confidence on the more general question of how likely we think it is that “the fundamentals will play out as or better than expected” for the company in question. This last question provides an opportunity for us to intuitively assign our own weights to all of the tangible and intangible elements of a company being successful.

In general, our global rating is very similar to the average rating of the sub question. When there is a deviation, we dig into why we think the whole is better than the sum of the parts to determine if there are intangible, hard to quantify aspects of the business that are not captured by the sub ratings, but which we think correctly support our higher global rating. That analysis sometimes validates the deviation in our global rating, while other times we recognize that our intuitive weighting was being driven by a bias (such as maybe really liking the management team and thus intuitively underweighting an only mediocre moat or higher cyclicality than we like to see).

Finally, we average the ratings to establish a single, quantitative conviction score. To buy a company, it must have an average rating of at least 2. Our highest conviction names score near to a 3 (it is extremely rare for a company to be assigned a “perfect” 3 rating). If a company is scored as a zero on any question, it become uninvestable for us. Any 1 ratings require a discussion. If there are multiple 1 ratings, we typically won’t invest in the company even if the average rating is a 2.

We believe that judgement around the long term outlook for companies is an inherently qualitative decision making process. However, by converting our qualitative judgement into quantitative scores we create a process by which we can make decisions on exactly how much of a stock we want to own and precisely differentiate between our portfolio of holdings, all of which we like and have a strong level of conviction in.

Readers familiar with the work of decision making researchers Phil Tetlock, Nate Silver, Annie Duke, and Daniel Kahneman will notice their thinking has greatly influenced the system we’ve developed. Kahneman, for instance, discussed a decision making process for identifying military recruits who might have the talent to become officers that used specific attribute questions as well as a “global” rating. Tetlock has extensively documented the need for forecasters to quantify the probability of an event occurring as well as making sure that forecasts are internally consistent with other forecasts made about the same topic. Duke explained the need for decision makers operating under conditions of uncertainty and time pressures to align and reconcile what Kahneman called System One, or reflexive decision making, and System Two or deliberative decisions making. And Nate Silver elegantly described how Bayesian statistics demonstrates how best to update your assessment of probabilities as you obtain new information.

While the literature on investing extensively documents how to evaluate and value a company, and financial planning literature comprehensively analyzes asset allocation decisions, bizarrely there is very little literature on how to size investments within a portfolio. The literature on this subject is often based on managing short term volatility of stock prices, rather than managing long term risk of permanent impair of capital. But lucky for us, the science of decision making has been more robustly explored when it comes to forecasting political events (Tetlock/Silver), sports events (Silver), gambling (Duke) and then we have Kahneman who literally won a Nobel Prize for his psychological insights to economic theory, particularly in the areas of judgment and decision-making under uncertainty.

In our next post, we’ll share a sample position sizing matrix and then finish up this series with a discussion of how we decide when to trade between stocks in our portfolio and how new stocks end up in our portfolio.

Please read important disclosures here.

Past performance is no guarantee of future results. All investments in securities carry risks, including the risk of losing one’s entire investment. The opinions expressed within this blog post are as of the date of publication and are provided for informational purposes only. Content will not be updated after publication and should not be considered current after the publication date. All opinions are subject to change without notice and due to changes in the market or economic conditions may not necessarily come to pass. Nothing contained herein should be construed as a comprehensive statement of the matters discussed, considered investment, financial, legal, or tax advice, or a recommendation to buy or sell any securities, and no investment decision should be made based solely on any information provided herein. Links to third party content are included for convenience only, we do not endorse, sponsor, or recommend any of the third parties or their websites and do not guarantee the adequacy of information contained within their websites. Please follow the link above for additional disclosure information.