All Models Are Wrong

A good model can be useful even when it fails. “It should be a given that whatever forecast we make on average will be wrong,” Ozonoff told me. “So usually it’s about understanding how it’s wrong, and what to do when it’s wrong, and minimizing the cost to us when it’s wrong.” The key is in remembering that a model is a tool to help us understand th

“All models are wrong, but some models are useful.”90 What he meant by that is that all models are simplifications of the universe, as they must necessarily be. As another mathematician said, “The best model of a cat is a cat.”91 Everything else is leaving out some sort of detail. How pertinent that detail might be will depend on…

Some highlights ha

Not every model applies to all situations. Part of building a latticework of mental models is about educating yourself regarding which situations are best addressed by which models. This takes some work and is not without error.

as the statistician George Box memorably put it, “All models are wrong, but some are useful.”

As we have seen, we can run into problems when we apply models to situations in which they don’t fit. If a model works, we must invest the time and energy into understanding why it worked so we know when to use it again. At the beginning the process is more important than the outcome. As you use the models, stay open to the feedback loops. Reflect

Any user of a map or model must realize that we do not understand a model, map, or reduction unless we understand and respect its limitations. If we don’t understand what the map does and doesn’t tell us, it can be useless or even dangerous.

we need to figure out which models are reliable and useful. We must also discard or update the unreliable ones, because unreliable or flawed models come with a cost.

statistician George Box once quipped, “All models are wrong; some models are useful,”