# Tag: Prediction

## Gradually Getting Closer to the Truth

You can use a big idea without a physics-like need for exact precision. The key to remember is moving closer to reality by updating.

Consider this excerpt from Philip Tetlock and Dan Gardner in Superforecasting

The superforecasters are a numerate bunch: many know about Bayes’ theorem and could deploy it if they felt it was worth the trouble. But they rarely crunch the numbers so explicitly. What matters far more to the superforecasters than Bayes’ theorem is Bayes’ core insight of gradually getting closer to the truth by constantly updating in proportion to the weight of the evidence.

So they know the numbers. This numerate filter is the second of Garrett Hardin‘s three filters we need to think about problems.

Hardin writes:

The numerate temperament is one that habitually looks for approximate dimensions, ratios, proportions, and rates of change in trying to grasp what is going on in the world.

[…]

Just as “literacy” is used here to mean more than merely reading and writing, so also will “numeracy” be used to mean more than measuring and counting. Examination of the origins of the sciences shows that many major discoveries were made with very little measuring and counting. The attitude science requires of its practitioners is respect, bordering on reverence, for ration, proportions, and rates of change.

Rough and ready back-of-the-envelope calculations are often sufficient to reveal the outline of a new and important scientific discovery … In truth, the essence of many of the major insights of science can be grasped with no more than child’s ability to measure, count, and calculate.

We can find another example in investing. Charlie Munger, commenting at the 1996 Berkshire Hathaway Annual Meeting, said: “Warren often talks about these discounted cash flows, but I’ve never seen him do one. If it isn’t perfectly obvious that it’s going to work out well if you do the calculation, then he tends to go on to the next idea.” Buffett retorted: “It’s true. If (the value of a company) doesn’t just scream out at you, it’s too close.”

Precision is easy to teach but it’s missing the point.

## Ten Commandments for Aspiring Superforecasters

The Knowledge Project interview with Philip Tetlock deconstructs our ability to make accurate predictions into specific components. He learned through his work on The Good Judgment Project.

In Superforecasting: The Art and Science of Prediction, Tetlock and Dan Gardner (his co-author) set out to distill the ten key themes that have been “experimentally demonstrated to boost accuracy” in the real world.

## 1. Triage

Focus on questions where your hard work is likely to pay off. Don’t waste time either on easy “clocklike” questions (where simple rules of thumb can get you close to the right answer) or on impenetrable “cloud-like” questions (where even fancy statistical models can’t beat the dart-throwing chimp). Concentrate on questions in the Goldilocks zone of difficulty, where effort pays off the most.

For instance, don’t ask, “Who will win the world series in 2050?” That’s impossible to forecast and unknowable. The question becomes more interesting when we come closer to home. Asking in April who will win the World Series for the upcoming season and how much justifiable confidence we can have in that answer is a different proposition. While we have low confidence in who will win, we can have a lot more than trying to predict the 2050 winner. At worst, we can narrow the range of outcomes. This allows us to move back on the continuum from uncertainty to risk.

Certain classes of outcomes have well-deserved reputations for being radically unpredictable (e.g., oil prices, currency markets). But we usually don’t discover how unpredictable outcomes are until we have spun our wheels for a while trying to gain analytical traction. Bear in mind the two basic errors it is possible to make here. We could fail to try to predict the potentially predictable or we could waste our time trying to predict the unpredictable. Which error would be worse in the situation you face?

## 2. Break Problems Down

This is Fermi-style thinking. Enrico Fermi designed the first atomic reactor. When he wasn’t doing that, he loved to tackle challenging questions such as “How many piano tuners are in Chicago?” At first glance, this seems very difficult. Fermi started by decomposing the problem into smaller parts and putting them into the buckets of knowable and unknowable. By working at a problem this way, you expose what you don’t know or, as Tetlock and Gardner put it, you “flush ignorance into the open.” It’s better to air your assumptions and discover your errors quickly than to hide behind jargon and fog. Superforecasters are excellent at Fermi-izing — even when it comes to seemingly unquantifiable things like love.

The surprise is how often remarkably good probability estimates arise from a remarkably crude series of assumptions and guesstimates.

## 3. Balance Inside and Outside Views

Echoing Michael Mauboussin, who cautioned that we should pay attention to what’s the same, Tetlock and Gardner add a historical perspective:

Superforecasters know that there is nothing new under the sun. Nothing is 100% “unique.” Language purists be damned: uniqueness is a matter of degree. So superforecasters conduct creative searches for comparison classes even for seemingly unique events, such as the outcome of a hunt for a high-profile terrorist (Joseph Kony) or the standoff between a new socialist government in Athens and Greece’s creditors. Superforecasters are in the habit of posing the outside-view question: How often do things of this sort happen in situations of this sort?

The planning fallacy is a derivative of this.

Belief updating is to good forecasting as brushing and flossing are to good dental hygiene. It can be boring, occasionally uncomfortable, but it pays off in the long term. That said, don’t suppose that belief updating is always easy because it sometimes is. Skillful updating requires teasing subtle signals from noisy news flows— all the while resisting the lure of wishful thinking.

Savvy forecasters learn to ferret out telltale clues before the rest of us. They snoop for nonobvious lead indicators, about what would have to happen before X could, where X might be anything from an expansion of Arctic sea ice to a nuclear war in the Korean peninsula. Note the fine line here between picking up subtle clues before everyone else and getting suckered by misleading clues.

The key here is a rational Bayesian updating of your beliefs. This is the same ethos behind Charlie Munger’s thoughts on killing your best-loved ideas. The world doesn’t work the way we want it to, but it does signal to us when things change. If we pay attention and adapt, we let the world do most of the work for us.

## 5. Everything is Connected

For every good policy argument, there is typically a counterargument that is at least worth acknowledging. For instance, if you are a devout dove who believes that threatening military action never brings peace, be open to the possibility that you might be wrong about Iran. And the same advice applies if you are a devout hawk who believes that soft “appeasement” policies never pay off. Each side should list, in advance, the signs that would nudge them toward the other.

[…]

There are no paint-by-number rules here. Synthesis is an art that requires reconciling irreducibly subjective judgments. If you do it well, engaging in this process of synthesizing should transform you from a cookie-cutter dove or hawk into an odd hybrid creature, a dove-hawk, with a nuanced view of when tougher or softer policies are likelier to work.

If you really want to have fun at meetings (and simultaneously decrease your popularity with your bosses), start asking what would cause them to change their minds. Never forget that having an opinion is hard work. You really need to concentrate and rag on the problem.

## 6. Remove Uncertainty

This could easily be called nuance matters. The more degrees of uncertainty you can distinguish, the better.

As in poker, you have an advantage if you are better than your competitors at separating 60/ 40 bets from 40/ 60— or 55/ 45 from 45/ 55. Translating vague-verbiage hunches into numeric probabilities feels unnatural at first but it can be done. It just requires patience and practice.

## 7. Balance Prudence and Decisiveness

Superforecasters understand the risks both of rushing to judgment and of dawdling too long near “maybe.” They routinely manage the trade-off between the need to take decisive stands (who wants to listen to a waffler?) and the need to qualify their stands (who wants to listen to a blowhard?). They realize that long-term accuracy requires getting good scores on both calibration and resolution— which requires moving beyond blame-game ping-pong. It is not enough just to avoid the most recent mistake. They have to find creative ways to tamp down both types of forecasting errors— misses and false alarms— to the degree a fickle world permits such uncontroversial improvements in accuracy.

## 8. Learn from Failure and Success

It’s easy to justify or rationalize your failure. Don’t. Own it and keep score with a decision journal. You want to learn where you went wrong and determine ways to get better. And don’t just look at failures. Evaluate successes as well so you can determine when you were just plain lucky.

## 9. Manage the Team

Master the fine art of team management, especially perspective taking (understanding the arguments of the other side so well that you can reproduce them to the other’s satisfaction), precision questioning (helping others to clarify their arguments so they are not misunderstood), and constructive confrontation (learning to disagree without being disagreeable). Wise leaders know how fine the line can be between a helpful suggestion and micromanagerial meddling or between a rigid group and a decisive one or between a scatterbrained group and an open-minded one.

## 10. Master the error-balancing bicycle.

Implementing each commandment requires balancing opposing errors. Just as you can’t learn to ride a bicycle by reading a physics textbook, you can’t become a superforecaster by reading training manuals. Learning requires doing, with good feedback that leaves no ambiguity about whether you are succeeding—“ I’m rolling along smoothly!”— or whether you are failing—“ crash!”

As with anything, doing more of it doesn’t mean you’re getting better at it. You need to do more than just go through the motions.  The way to get better is deliberate practice.

## And finally …

“It is impossible to lay down binding rules,” Helmuth von Moltke warned, “because two cases will never be exactly the same.” Guidelines (or maps) are the best we can do in a world where nothing represents the whole. As George Box said: “All models are false. Some are useful.”

***

## Article Summary

• Focus on questions where effort will pay off the most.
• When the problem is big and seemingly intractable, break it down into crude smaller components.
• As we are prone to look at things from the inside out, remember to ask the outside-in questions.
• We are never 100 percent confident, update your beliefs as new information becomes available.
• There is always more than one side to problems. Understanding the counterarguments is the key to having an informed opinion.
• Remove as much uncertainty as you can.
• Rushing to judgement can be as harmful as taking too long to make a decision.
• There are levels to learning. Learning from your failures is good. Learning from others’ failures is better. But learning from success is key.
• When teams make decisions, managing the process is critical.
• No amount of book smarts will help you, you have to practice.