Paul R. Yarnold, Ph.D., Nathaniel J. Rhodes, Pharm.D., Ariel Linden, Dr.P.H.
Optimal Data Analysis, LLC; Chicago College of Pharmacy, Midwestern University; Linden Consulting Group, LLC
Overviews of optimal discriminant analysis (ODA) and novometric theory are presented. Discussion addresses the role of accuracy in translational and precision forecasting research, and of parsimony in theoretical research; the structure of maximum-accuracy univariable and multivariable models; underlying theoretical axioms; assessing statistical significance; identifying the descendant family of all unique statistically viable models within a sample; paradoxical confounding; precision forecasting architecture; ordered and temporal models; and future research directions. Discussion applies to all empirical research designs involving non-Hilbert space.