Access Type
Open Access Dissertation
Date of Award
January 2016
Degree Type
Dissertation
Degree Name
Ph.D.
Department
Education Evaluation and Research
First Advisor
Sholmo Sawilowsky
Abstract
The Sawilosky's I-Test was developed to as an alternative method to evaluate construct validity, more specifically, in regards to the Multitrait-Multimethod Matrix designed by Campbell and Fiske (1959). Typically, researchers use a method by Campbell and Fiske that involves a subjective “physical” look at the matrix to determine validity. Sawilowsky’s I-Test offers a statistical approach that incorporates the current practice but removes the subjectivity involved in this process.
There are only two existing studies that look at the I-Test, Sawilowsky in 2002 and Cuzzocrea in 2007. Both studies found that although the I-Test is not a perfect statistic, it provides an objective method to analyze a Multitrait-Multimethod Matrix when looking at construct validity. Neither of these studies used raw data to test this statistic. This study collected data in attempt to use a “real world” application of this statistics and provide additional research on this statistic’s potential application.
The Sawilowsky I-test has the potential for testing construct validity in studies with criminal populations. Although this findings did not support construct validity, there was some potential (CDF=.18) for evidence of construct validity. Future studies should include demographics and consider using the expanded scales as they were originally developed.
Recommended Citation
Child, Holly Ann, "Distribution-Free Trends Test To Determine The Construct Validity Of An Anti-Social Criminal Attitudes Scale" (2016). Wayne State University Dissertations. 1434.
https://digitalcommons.wayne.edu/oa_dissertations/1434
Included in
Criminology and Criminal Justice Commons, Psychology Commons, Statistics and Probability Commons
