U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Size Matters: Standard Errors in the Application of Null Hypothesis Significance Testing in Criminology and Criminal Justice

NCJ Number
217854
Journal
Journal of Experimental Criminology Volume: 2 Issue: 1 Dated: Spring 2006 Pages: 1-22
Author(s)
Shawn D. Bushway; Gary Sweeten; David B. Wilson
Date Published
2006
Length
22 pages
Annotation
This literature review assessed the state of the criminological and criminal justice application of Null Hypothesis Significance Testing (NHST), which is the main approach of social sciences for empirically examining hypothesized relationships and establishing the importance of empirical results.
Abstract
The literature review indicates that most researchers provide the basic information necessary for understanding effect sizes and analytical significance in tables that include descriptive statistics and some standardized measure of size, for example, betas and odds ratios. On the other hand, few of the research reports mention statistical power, and even fewer discuss the standard by which a finding would be considered large or small. In addition, less than half of the reports distinguish between analytical significance and statistical significance. Most reports used the term "significance" in ambiguous ways. The literature review applied a modified version of the instrument used in 2 reviews of the economics literature by McCloskey and Ziliak in order to code 82 articles in criminology and criminal justice. Three sources of papers were selected: "Criminology," "Justice Quarterly," and a recent review of experiments in criminal justice by Farrington and Welsh. 3 tables, 6 notes, and 121 references

Downloads

No download available

Availability