Distribution-Free Trends Test To Determine The Construct Validity Of An Anti-Social Criminal Attitudes Scale

<p>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. </p> <p>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. </p> <p>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.</p>

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Open Access Dissertation

Discipline thesis:degree_discipline

Education Evaluation and Research

Year dc:date.available

2016

Author dc:creator

• Child, Holly Ann

Contributors dc:contributor

• Sholmo Sawilowsky

• Construct Validity
• distribution free
• I-test
• multitrait-multimethod matrix
• Sawilowsky
• trends test
• Criminology and Criminal Justice
• Psychology
• Statistics and Probability

Repository record dc:identifier

https://digitalcommons.wayne.edu/oa_dissertations/1434

OAI identifier oai:identifier

oai:digitalcommons.wayne.edu:oa_dissertations-2433