Accurate Quote by Elliott Sober
“It is an interesting fact about model selection that the evidence at hand can indicate that a model known to be false will be more predictively accurate than a model known to be true. This opens the door to a kind of instrumentalism.”
About This Quote
Sometimes a false model predicts better than a true one, suggesting practical usefulness can outweigh factual accuracy.
In simple terms: False models can be more useful than true ones.
Prioritize predictive performance over truth.
Themes
Mood
Type
When to use this quote
- machine learning
- policy making
- medical diagnosis
- economic forecasting
Key Concepts
Questions to Reflect On
- When should we trust a false model?
- What are the risks of instrumentalism?
Reliance on false models may mislead decisions.