A Rasch Model Analysis of the Psychometric Properties of the Student-Teacher Relationship Scale among Middle School Students

The current study investigated Student-Teacher Relationship Measure (STRM) psychometric properties using Rasch analysis in a sample of middle school female students (N = 995). Rasch Principal Components Analysis revealed psychometric support of two subscales (i.e., Academic and Social Relations). Su...

Full description

Saved in:
Bibliographic Details
Published in:European journal of educational research 2021-04, Vol.10-2021 (volume-10-issue-2-april-2021), p.957-973
Main Authors: Alhadabi, Amal, Aldhafri, Said
Format: Article
Language:English
Subjects:
Eğitim Bilimleri
Females
Item Response Theory
Measures (Individuals)
Middle School Students
Psychometrics
Rating Scales
Student Characteristics
Teacher Student Relationship
Test Items
Test Reliability
Test Validity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The current study investigated Student-Teacher Relationship Measure (STRM) psychometric properties using Rasch analysis in a sample of middle school female students (N = 995). Rasch Principal Components Analysis revealed psychometric support of two subscales (i.e., Academic and Social Relations). Summary statistics showed good psychometric properties. The category structure and individual statistics (i.e., items and person infit and outfit) were not ideal. Category structure showed that the distances between adjacent thresholds were lower than optimal criteria. Even though findings indicated that items mean square statistics (MNSQ) were optimal, standardized fit statistics (i.e., ZSTD) reflected many misfit persons and items in each subscale. After eliminating the misfit persons and items, the two subscales met the Rasch optimal criteria. The updated short 22-item scale had good psychometric properties, high item and person separation, and good item and person reliability for the two subscales and can be used as a reliable and valid scale.
ISSN:2165-8714
2165-8714
DOI:10.12973/eu-jer.10.2.957