ABSTRACT
One of the data set's requirements for the module is to be comprised of the variables of the data envelopment analysis (DEA) model and contextual variables. The research problem deals with the identification of the risk factors responsible for decreasing retention rate among the sophomore students caused by low GPA. Running the analysis in the phase is a straightforward affair, where the only decisions to be made are regarding the assumption of the return-to-scale and the orientation of the model. In the case of the scenario for the module, input-oriented DEA under variable return to scale would be an appropriate choice of options. One of the goals of Phase 2 is to match the results of the DEA to the results of cluster analysis – it could be very useful to identify those clustering solutions, which result in the greatest difference between the clusters in terms of the averaged scores of the DEA.
