Item response theory (IRT) offers several advantages compared to classical test theory (CTT) in providing additional information on psychometric qualities of the scale. My goal was to demonstrate the superiority of IRT as compared to CTT through two analyses of the Top Leadership Direction scale (TLDS), which was created to measure the effectiveness of top leadership through the followers’ perceptions in the context of providing guidance of the organization. Furthermore, the participants (n = 8046) were the employees from various positions at 18 of the 23 California State University campuses. In the graded response model (GRM) analysis, the result showed that IRT provided more information about each item and allowed a useful visual inspection of the items. With the second analysis, I aimed to provide evidence of measurement equivalence across functional groups of employees using differential item functioning (DIF) analysis in IRT. Due to the lack of model fit, the DIF analysis was incomplete. A supplementary multigroup CFA was conducted to investigate the structural difference across the groups for the items of the TLDS. The result of multigroup CFA suggested that item 2 and item 4 did not show measurement equivalence across the groups at the construct level. An alternative model in IRT was discussed due to some limitations of GRM in the present study. Practical and theoretical implications for the use of IRT were also presented and contrasted with CTT.
| Identifer | oai:union.ndltd.org:csusb.edu/oai:scholarworks.lib.csusb.edu:etd-1429 |
| Date | 01 June 2016 |
| Creators | Lee, Jung-Jung |
| Publisher | CSUSB ScholarWorks |
| Source Sets | California State University San Bernardino |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | Electronic Theses, Projects, and Dissertations |
Page generated in 0.0143 seconds