NotesFAQContact Us
Search Tips
ERIC Number: ED546424
Record Type: Non-Journal
Publication Date: 2012
Pages: 152
Abstractor: As Provided
Reference Count: N/A
ISBN: 978-1-2676-3303-3
Contextual Differential Item Functioning: Examining the Validity of Teaching Self-Efficacy Instruments Using Hierarchical Generalized Linear Modeling
Zhao, Jing
ProQuest LLC, Ph.D. Dissertation, The Ohio State University
The purpose of the study is to further investigate the validity of instruments used for collecting preservice teachers' perceptions of self-efficacy adapting the three-level IRT model described in Cheong's study (2006). The focus of the present study is to investigate whether the polytomously-scored items on the preservice teachers' self-efficacy survey function the same across gender and within different school contexts. Hence, the present study also explores contextual DIF. To serve the purpose, the study used data collected by the TQP research team which elicited preservices teachers' self-efficacy beliefs using "Teachers' Sense of Efficacy Scale" ("TSES") and "Teachers' Efficacy Scale" ("TES"). Participants included 1485 secondary preservice teachers who were pursuing their licensures at 45 universities and colleges in the State of Ohio in the years of 2006-2007 and 2007-2008. Six research questions were put forward based on the literature. Several quantitative methods--Confirmatory Factor Analysis (CFA), Rasch/rating scale analyses, and multilevel IRT analyses--were used to answer the six research questions. The results showed that Rasch/rating scale model and multilevel IRT model had the same results for TSES subscales 2 and 3. The two procedures are comparable in detecting DIF items for these subscales. However, they are not comparable in terms of detecting DIF items for TSES subscale 1, TES subscales 1 and 2. The possible reasons for the different results are discussed. In addition, when the context predictor was added to the multilevel model, the results changed for the DIF items. In general, the four-step procedure in Cheong's study (2006) worked well for the present sample. The present study, in the methodological sense, tests the applicability of the three-level model of Cheong to polymotous data which are more often used in the field of education and psychology. In addition, study takes the contextual sources of DIF into account to see whether the context exerts any impact on gender DIF as the context might be one of the sources for DIF items. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page:]
ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site:
Publication Type: Dissertations/Theses - Doctoral Dissertations
Education Level: Higher Education; Postsecondary Education; Secondary Education
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Identifiers - Location: Ohio
Identifiers - Assessments and Surveys: Teacher Efficacy Scale