Konfigurale auswertung von daten aus pratest-posttest kontrollgruppen designs

For treatment evaluation in multivariate pretest-posttest designs, methods of Configural Frequency Analysis (CFA) are recommended. Specifically, three CFA methods are proposed: (1) Prediction CFA, (2) Interaction CFA, and (3) Generalized Unary Hypothesis Analysis (GUHA) CFA. These methods share in common that they define treatment response-relations via so-called types, that is local or regional associations among the factors of a treatment- response cross-classification. Unit of analysis for these CFA approaches are difference scores between the first and second observation. Numerical examples use data from an experiment on the effects of training methods on calculation and reasoning in learning disabled school children.