February, 2003
© 2001, 2003 Scott S. Emerson M.D., Ph.D.
 Nonparametric Models: 11
The Problem
In the development of statistical models, and even moreso in the teaching of statistics, parametric probability models have received undue emphasis
Examples:
·t test is typically presented in the context of the normal probability model
·theory of linear models stresses small sample properties
·random effects specified parametrically
·Bayesian (and especially hierarchical Bayes) models are replete with parametric distributions