Testing models and measurement invariance of the learning gains scale

This study tested the construct validity, factorial validity, and measurement invariance of the learning gains scale based on survey responses of a large sample (n = 536) of undergraduate students in two colleges at a university in Ethiopia. The analyses were performed through structural equation modeling technique using the stata 13 data analysis and statistical software package. The results demonstrate a 3-factor model representing the underlying construct satisfying the different model goodness-of-fit statistics and practical indexes. The observed factor loadings of variables within each factor and the correlations between the factors provide supporting evidence of construct validity. Measurement invariance tests were also confirmed acceptable levels of measurement equivalence between groups. Implications of the 3-factor model in higher education research are discussed.