Student dropout is a major concern in studies investigating higher education retention strategies. However, studies investigating the optimal time to identify students who are at risk of withdrawal and the type of data to be used are scarce. Our study consists of a withdrawal prediction analysis based on classification trees using both sociodemographic and academic data from 935 first-year students at an engineering school in Spain. We build prediction models using information collected at three different moments throughout the first semester of the students’ first university year. Our results echo those of previous studies supporting the need for an early first-year intervention to prevent non-completion. In addition, academic performance data serve as a good predictor. Finally, academic monitoring throughout the first semester improves the prediction accuracy, challenging the demand for ‘as soon as possible’ identification of students who are at risk of dropout.

Purpose: Based on Azjen’s (1991) theory of planned behavior, the purpose of this paper is to complement the existing body of knowledge on entrepreneurial intentions (EIs) by comparing two different university environments in Spain (online and face-to-face) and their impact on EIs of university students using two components of social capital (SC), trust and network ties as variables with influence on the antecedents of EIs.Design/methodology/approach: A survey was administered to online and face-to-face students yielding a total sample of 302 and 204, respectively. Partial least square–structural equation modeling is the technique employed to perform the analysis.Findings: SC has a significant influence on EIs in both environments with greater effects online, as a consequence of the mediated role played by network ties between trust and the attitude toward the behavior, the subjective norm and consequently, EIs.Research limitations/implications: The authors used a cross-sectional method. However, it would be interesting to obtain longitudinal data to provide a more valid support for the study.Practical implications: This study provides insight into the important role played by network ties based on trust in the entrepreneurship process and in the university environment.Originality/value: This study contributes to understanding the differential impact of SC (trust and network ties) on the antecedents of EIs between the students enrolled in different university environments using two non-parametric techniques Henseler’s multigroup analysis and the permutation test.