z-logo
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.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here