NCJ Number
183347
Journal
Crime and Delinquency Volume: 46 Issue: 3 Dated: July 2000 Pages: 425-434
Date Published
July 2000
Length
10 pages
Annotation
This article uses data from the San Diego Navy Experiment to illustrate how findings from nonexperimental evaluations of programs designed to treat men who abuse their cohabitant partners may lead to erroneous conclusions.
Abstract
To illustrate the need for randomized experimental group-control group research designs, the results of the San Diego Navy Experiment are examined with and without the use of a randomized control group. The conclusions reached without the use of a control group are much different than those reached when data from the control group were included in the analyses. It is clear that if an experimental design for the San Diego Navy Experiment had not included a non-services control group, the interpretation of the findings would have been erroneous, with all of the attendant consequences. Unfortunately, because of the difficulties associated with using experimental group-control group research designs, researchers continue to conduct nonexperimental evaluations of interventions of all kinds, producing findings that are impossible to interpret accurately. Furthermore, nonexperimental research does not address the basic questions that program evaluations should address: Do those in treatment fare better than those receiving no treatment? Are those who participate in treatment programs better off than those who do not participate? Do the interventions in question do more good than harm? 3 tables and 9 references