Since all models are wrong the scientist cannot obtain a “correct” one by excessive elaboration.
- All models are wrong, so putting more effort than necessary will not yield the “right” model.
- http://www.jstor.org/stable/2286841?seq=1#page_scan_tab_contents
- Box, G. E., 1976. Science and statistics. Journal of the American Statistical Association, 71(356), pp.791-799.
http://d.hatena.ne.jp/himaginary/20160925/glasner_on_all_models_are_false
- David Glasner took Paul Romer’s critique of macroeconomics and made the following assertions.
- Macroeconomists counter that “all models are wrong,” but microfoundation models have not escaped Lucasian criticism either.
- The Friedman assertion that the more important the theory, the more unrealistic the assumptions is also used, but the word “simple” should have been used rather than “unrealistic”.
- The phrase “all models are wrong” originated in a paper by George Box, the gist of which is as follows
- Models should aim for a conservative depiction without over-elaboration.
- Scientists need to be careful about which mistakes are important.
- When applying mathematics, make untrue but useful assumptions.
- The usefulness of a statistical technique is not known until it is used.
- Major advances in science occur in the back-and-forth between theory and practice.
- Modern macroeconomists flaunt advanced mathematical techniques, but they should be a bit more humble if they accept the content of Box’s lecture.
All models are wrong - Wikipedia
relevance - Occam’s razor - thought economy theory - Relativization of correctness What is correctness?
This page is auto-translated from /nishio/すべてのモデルは間違っている using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.