Ellen D'Haenens

Multilevel Exploratory Factor Analysis: Illustrating Its Surplus Value in Educational Effectiveness Research.

This paper illustrates the surplus value of multilevel exploratory factor analysis in educational effectiveness research. Educational researchers often use measures for process variables at the class or school level to explain differences in student outcomes. Recently, van de Vijver and Poortinga (2002) have developed a procedure for multilevel exploratory factor analysis which can be extremely useful in this kind of application. Their procedure, which is based on the “multilevel confirmatory factor analysis” framework of Muthén (1994), is demonstrated by means of constructing measures for school process variables based on teacher data. Every step of the procedure is nicely illustrated and commented on using these data. Furthermore, the meaning of the findings and challenges when using multilevel exploratory factor analysis are emphasized.

Student achievement and academic self-concept among secondary students in Flanders: gender and changes over time

This study investigated the causal ordering between general academic self-concept and academic achievement from Grade 7 to Grade 12 of secondary school by repeated assessment of 2834 Flemish adolescents. Age and sex differences were tested using structural equation modelling. Our results supported a moderate reciprocal effects model, indicating that previous achievement had a positive effect on subsequent academic self-concept and that previous academic self-concept had a positive effect on subsequent academic achievement. Furthermore, an interesting developmental pattern was observed as students move through secondary school. Between Grades 7 and 8, our results showed no relation between academic self-concept and achievement. Subsequently, between Grades 8 and 10, a self-enhancement model was supported, whereas in the final years of secondary school, a full reciprocal effects model was found. Finally, small gender differences were observed in the causal relation between academic self-concept and achievement. The discussion addresses both methodological and theoretical issues in self-concept research. The practical implications of the results are discussed briefly.

Linking student outcome variables with school process variables: multilevel confirmatory factor analysis takes precedence

In the current study, we investigated the relationship of constructed measures for school process variables with distinct student outcome variables, including one measure for student achievement and one psychosocial outcome variable. Two different approaches were used to develop these school process measures: standard confirmatory factor analysis plus aggregation on the one hand (i.e., the traditional approach) and multilevel confirmatory factor analysis on the other hand (i.e., the alternative approach). The main research objective involved the comparison between these two approaches. It was found that the alternative approach could yield different conclusions in comparison with the more traditional approach. Therefore, these results underline the importance of using the most appropriate approach to develop measures for school process variables, which is the alternative approach that explicitly takes into account the hierarchical nature of the data collected on school processes.