How large are the error bars?

“Error bars are graphical representations of the variability of data and used on graphs to indicate the error or uncertainty in a reported measurement.” (Source: Wikipedia) When we make predictions or estimates, it’s helpful to recognize that there’s an error rate. Some predictions are more prone to error than others. Predicting the price of milk at my local supermarket tomorrow is less error-prone than predicting the average ticket price of regional air transportation in seven years. Mental shortcuts make us want to treat all predictions as equally (very) accurate, but it’s helpful to stop and consider how big the error bars might be. Reading this, it’s easy to think, “Well, I don’t make predictions all that often.” But as Thinking in Bets author Annie Duke explained decisions are predictions about the future. Recognizing where my predictive abilities are weak (and my error bars are large) is a practice in awareness and humility, and I look to keep working on it.