Law and Statistical Disorder: Statistical Hypothesis Test Procedures and the Criminal Trial Analogy

13 Pages Posted: 10 Mar 2006  

Tung Liu

Ball State University - Department of Economics

Courtenay C. Stone

Ball State University - Department of Economics

Date Written: May 16, 2007

Abstract

Virtually all business and economics statistics texts incorporate some more-or-less detailed discussion of the similarities between conducting hypothesis tests and criminal trials. Apparently, the authors of these texts believe that students will be better able to understand the relevance and usefulness of hypothesis test procedures by introducing them via the dramatic analogy of the criminal justice system. In this paper, we show that the criminal trial analogy commonly used by business and economics statistics textbook authors to motivate, illustrate and/or demonstrate hypothesis test procedures represents bad statistics and bad pedagogy. We then show how the criminal trial setting can be used correctly to illustrate some important statistical concepts.

Keywords: hypothesis tests, criminal trials, Neyman-Pearson hypothesis test procedures

JEL Classification: A22, C12, K14

Suggested Citation

Liu, Tung and Stone, Courtenay C., Law and Statistical Disorder: Statistical Hypothesis Test Procedures and the Criminal Trial Analogy (May 16, 2007). Available at SSRN: https://ssrn.com/abstract=887964 or http://dx.doi.org/10.2139/ssrn.887964

Tung Liu

Ball State University - Department of Economics ( email )

Muncie, IN 47306-0340
United States
765-285-5360 (Phone)
765-285-4313 (Fax)

Courtenay C. Stone (Contact Author)

Ball State University - Department of Economics ( email )

Muncie, IN 47306-0340
United States
765-285-2857 (Phone)
765-285-4313 (Fax)

Paper statistics

Downloads
192
Rank
129,670
Abstract Views
3,717