Publication Date
2022
Document Type
Thesis
Committee Members
Nathan Bowling, Ph.D. (Advisor); Anthony Gibson, Ph.D. (Committee Member); Corey Miller, Ph.D. (Committee Member)
Degree Name
Master of Science (MS)
Abstract
Research has demonstrated that careless responding (CR) threatens the construct validity of measures (see Huang et al., 2015; Wise & Kong, 2005). Researchers have developed and studied many measurement approaches to capture CR in surveys, with different survey measures compensating for the practical or empirical limitations of other measures. This research is distinguished from ability test CR research because ability tests are fundamentally different from surveys. Within ability tests, CR research has focused only on response time and self-report measures of CR, both of which carry limitations. The former is inflexible because the index necessitates item-level response time information, and therefore cannot be used in pen-and-paper tests or online tests without such item-level information available. The latter index is plagued by theoretical and empirical shortcomings. Thus, the purpose of my study is to find a comparably valid and more flexible approach through testing the efficacy of five survey CR measurement approaches, namely the infrequency approach, instructed-response approach, the consistency approach, the self-report approach, and long-string analysis, in capturing CR in tests. In a sample of 291 undergraduate students, I found strong support for using the infrequency approach to assess careless responding, weak support for the instructed-response approach and long-string analysis, and no support for the self-report or consistency approaches.
Page Count
198
Department or Program
Department of Psychology
Year Degree Awarded
2022
Copyright
Copyright 2022, all rights reserved. My ETD will be available under the "Fair Use" terms of copyright law.
ORCID ID
0000-0001-5366-5303
