A Confirmatory Factor Analysis of Content Coverage Measure Using Multiply Imputed Datasets

This paper re-examined the validity of the content coverage measure, which is a proxy for opportunity to learn (OTL), by employing a confirmatory factor analysis (CFA) on five multiply-imputed datasets. Data for this study were drawn from the PISA 2012 Malaysian sample. Specifically, we used a sample of 4247 students from 135 Malaysian national secondary schools. The PISA 2012 content coverage measure comprised four constructs, namely experience with applied mathematics tasks at school, experience with pure mathematics tasks at school, familiarity with mathematical concepts and experience with various types of problems at school. Prior to conducting the CFA, missing data resulted from student questionnaire rotation design were multiply-imputed using predictive mean matching (PMM) estimation via R-package Multivariate Imputation by Chained Equations (MICE). Subsequently, we conducted the CFA using R-package lavaan.survey that incorporates multiply-imputed data and survey weights as well as non-normality of data through its Maximum Likelihood Robust (MLR) estimation. After a few cycles of theory-guided model specification involving deletion of several items with low factor loadings, examination of various fit indices, and inspections of Composite Reliability (CR) and Average Variance Extracted (AVE) values, results showed that the final congeneric CFA model for the content coverage measure provided good fit to the data.