Testing Factorial Validity and Gender Invariance of the Survey of Attitudes toward Statistics Scale

• Main Authors: Prashanth, Talwar, Nur Fatihah, Abdullah Bandar
• Format: Article
• Language: English
• Published: Wolters Kluwer - Medknow 2023
• Subjects: H Social Sciences (General)
• Online Access: http://ir.unimas.my/id/eprint/42786/3/Testing.pdf; http://ir.unimas.my/id/eprint/42786/; https://journals.lww.com/mjp/Fulltext/2023/01000/Testing_Factorial_Validity_and_Gender_Invariance.5.aspx
• Institution: Universiti Malaysia Sarawak

Objective: The main goal of this study was to test the psychometric properties of the Survey of Attitudes Towards Statistics (SATS‑36) among undergraduate students. Materials and Methods: Cross‑sectional study was conducted among a sample comprising of 218 undergraduate students at University Malaysia Sarawak. A convenience sampling technique was implemented while selecting participants. The self‑report questionnaire consisted of two parts. The first section included the socio‑demographic characteristics of participants, such as age, gender, and ethnicity. The second section was the Survey of Attitudes Towards Statistics(SATS‑36). Exploratory factor analysis(EFA) and confirmatory factor analysis(CFA) was used to arrive at the best factor solution. To assess factor invariance, multi‑groupCFA was performed. Results: Descriptive statistics of students’ attitudes toward statistics revealed that most of the students held positive attitudes toward statistics. EFA analysis deemed to have produced the incorrect factor structure as most items were misclassified on the wrong factor. CFA suggested a 6‑factor solution with 30 items. Thus the 36 items were reduced to SATS‑30. The goodness‑of‑fit statistics for the SATS‑30 showed a passable model fit. Responses of male and female students to the SATS‑30 were then examined to explore scale invariance across gender. Consistency was found across two groups. This was, furthermore, supported by the assessment of composite reliability which was also found to be relatively high. Conclusion: The present findings are consistent with extant research literature on factor structure and invariance of the Survey of Attitudes Toward Statistics scale. Further research on SATS‑30 could include longitudinal studies in order to analyze causality.