Teaching Prediction Intervals

Abstract

Teaching prediction intervals to introductory audiences presents unique opportunities. In this article I present a strategy for involving students in the development of a nonparametric prediction interval. Properties of the resulting procedure, as well as related concepts and similar procedures that appear throughout statistics, may be illustrated and investigated within the concrete context of the data. I suggest a generalization of the usual normal theory prediction interval. This generalization, in tandem with the nonparametric method, results in an approach to prediction that may be systematically deployed throughout a course in introductory statistics.