Considerations Across Three Cultures: Parametric Regressions, Interpretable Algorithms, and Complex Algorithms

The relevance of the themes presented in "Statistical Modeling: The Two Cultures" by Leo Breiman remains twenty years later. While we could consider many categorizations of statistics culture, we posit that at least three cultures have emerged. We still have the data modeling group with regressions defined within parametric models, but the algorithmic modeling culture has, at a minimum, bifurcated with interpretable algorithms and (possibly explainable) complex algorithms [Rudin, 2019]. Practitioners of algorithmic modeling may develop interpretable or complex algorithms or both, depending on the needs of the scientific question. As empirically driven statisticians, we would prefer to collect data on this before putting forth a supposition, but, in lieu of such data, we also surmise that the algorithmic modeling culture has grown larger over time than Breiman's proposed 2% of statisticians. In this commentary, we remark on several areas of increasing concern for statisticians--in all three cultures--working to solve real, substantive problems.