Bivariate logistic models for the analysis of the students' University "success"

We analyze the students’ success at University by considering their performancein terms of both “qualitative performance”, measured by their grade average,and “quantitative performance”, measured by University Credits accumulated. Tojointly model both marginal and association relationships with covariates, the analysishas been carried out by fitting a bivariate ordered logistic model (BOLM), ina nonparametric fashion, by penalized maximum likelihood estimation. The advantagesof such model are in terms of parsimony and parameters interpretation, whilepreserving goodness-of-fit. The application regards an engineering student (ES) cohortfrom the University of Palermo.