Statistical Modeling: The Two Cultures, by Leo Breiman
There are two cultures in the use of statistical modeling to reach conclusions from data. One assumes that the data are generated by a given stochastic data model. The other uses algorithmic models and treats the data mechanism as unknown - read the full paper.
In this paper, Breiman reviews:
- His road map
- Projects in consulting
- Return to the university
- The use of data models
- The limitations of data models
- Algorithmic modeling
- Rashomon and the multiplicity of good models
- Occam and simplicity vs. accuracy
- and more!
Read this important paper provided by Salford Systems at no cost.