Premium
In praise of partially interpretable predictors
Author(s) -
Le Tri,
Clarke Bertrand
Publication year - 2020
Publication title -
statistical analysis and data mining: the asa data science journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.381
H-Index - 33
eISSN - 1932-1872
pISSN - 1932-1864
DOI - 10.1002/sam.11450
Subject(s) - interpretability , predictive power , series (stratigraphy) , mean squared error , parametric statistics , variety (cybernetics) , computer science , praise , parametric model , mathematics , mean squared prediction error , univariate , artificial intelligence , machine learning , statistics , multivariate statistics , psychology , paleontology , philosophy , epistemology , psychotherapist , biology
Often there is an uninterpretable model that is statistically as good as, if not better than, a successful interpretable model. Accordingly, if one restricts attention to interpretable models, then one may sacrifice predictive power or other desirable properties. A minimal condition for an interpretable, usually parametric, model to be better than another model is that the first should have smaller mean‐squared error or integrated mean‐squared error. We show through a series of examples that this is often not the case and give the asymptotic forms of a variety of interpretable, partially interpretable, and noninterpretable methods. We find techniques that combine aspects of both interpretability and noninterpretability in models seem to give the best results.