Factor Structure, Reliability and Validity of Attitudes of Biostatistics Scale
Muhammad Shafiq Harun *
School of Informatics and Applied Mathematics, University Malaysia Terengganu, 21030 Kuala Terengganu, Malaysia.
Sabri Ahmad
School of Informatics and Applied Mathematics, University Malaysia Terengganu, 21030 Kuala Terengganu, Malaysia.
*Author to whom correspondence should be addressed.
Abstract
Confirmatory Factor Analysis (CFA) has been used for most of researchers nowadays to evaluate the goodness of fit of measurement model using structural equation modeling. The aim of this study to evaluate the factors used to validate the best model of four latent construct by using pooled confirmatory factor analysis (PCFA) technique on variable student’s attitude toward Biostatistics and to assess dimensions of students’ attitudes regarding Biostatistics courses. A survey adapted from Survey of the Attitudes toward Statistics (SATS) was employed to observe student’s attitude toward a Biostatistics course. The data be collected through questionnaires distributed to first year students at a higher education institution. The data were analysed through four model which is model specification, model estimation, model evaluation, and model modification by using Analysis Moment of Structural (AMOS) in order to improve the validity of each latent construct. The result showed that the validity and reliability of all latent variables is achieved and the pooled CFA technique is more efficient.
Keywords: Pooled confirmatory factor analysis, factor structure, unidimensionality, validity, reliability and latent variables.