Second-Order Confirmatory Factor Analysis of the Reactions to Tests Scale with Cross-Validation

The need for additional theoretical and empirical research on the cross-validation of covariance models was discussed, with results indicated that a reduced 20-item RTT scale fit the data better than the 40-item original RTT and that a second-order structure explained the data very well.

Abstract

The factor structure of the RTT was evaluated by testing a series of confirmatory factor models including a second-order structure. The results indicated that a reduced 20-item RTT scale fit the data better than the 40-item original RTT and that a second-order structure explained the data very well. The models were cross-validated using several strategies. The reduced RTT was found not to cross-validate in terms of overall fit. However, when the parameter estimates were tested across samples, all parameters were found to be invariant except the item residuals. Because the cross-validation results were not conclusive, the need for additional theoretical and empirical research on the cross-validation of covariance models was discussed.