uncertainty
A condition in which future outcomes cannot be known from past data because the future may genuinely differ from the past, as distinct from quantifiable risk.
As defined in Russ Roberts on Education
Where it comes up · 4
- Gerd Gigerenzer on Gut Feelings5 claims
- Russ Roberts on Education1 claim
- Gerd Gigerenzer on How to Stay Smart in a Smart World1 claim
- 302 - Science Civilization1 claim
Most important claims · 8 of 8Search all claims for “uncertainty” →
- Institutions should stop telling the public about 'errors' in measurement, since the public hears 'mistakes,' and instead communicate 'uncertainties'—a fundamental feature of all data that the next experiment is designed to reduce, building greater confidence; this distinction is not taught and was badly needed during COVID.302 - Science Civilization
- Complex methods work best at explaining the past, but under uncertainty where prediction is needed you must scale back to simpler tools; a fast-and-frugal tree using three factors can outperform logistic regression in predicting heart-patient outcomes going forward, while also being understandable to doctors and adaptable when the patient population changes.Gerd Gigerenzer on Gut Feelings
- More information is not always better; in a world of risk fine-tuning means more information helps (ignoring costs), but under uncertainty heuristics do better with only a certain intermediate amount of information, as the bias-variance dilemma explains why a reduction of information can be helpful.Gerd Gigerenzer on Gut Feelings
- Value at Risk would be a great tool if finance were predictable (a world of calculable risk), but real finance is high uncertainty; calculating a large bank's VaR requires estimating thousands of risk parameters and millions of correlations from 5-10 years of data, which borders on astrology rather than science, and VaR calculations have not prevented any crisis while fostering an illusion of certainty.Gerd Gigerenzer on Gut Feelings
- You cannot know how much the stock market will fall in the next year based on the past, because the future could differ from the past; even if an exchange has never fallen more than 12% in 100 years, that does not mean it cannot fall more than 12% next year.Russ Roberts on Education
- When all probabilities, outcomes, and consequences are known (a world of risk like roulette or a lottery), calculation is best; but in situations of uncertainty—investing, marriage, hiring—where probabilities cannot be known or even estimated and future states are unknown, precise calculation is an illusion and robust rules of thumb are superior.Gerd Gigerenzer on Gut Feelings
- The human brain evolved to deal with uncertainty rather than situations of calculable risk or lotteries, becoming amazing at taking up subtle contextual cues; it would not work well if it merely thought logically, because language is inherently ambiguous and people immediately grasp intended meanings from context.Gerd Gigerenzer on Gut Feelings
- There is a general principle that if the world is stable—like a well-defined game—algorithms will most likely beat humans and perform much better, but if there is lots of uncertainty, as in cancer treatment or investment, then algorithmic claims are probably overstated and one must be very cautious.Gerd Gigerenzer on How to Stay Smart in a Smart World