Title: Measuring efficiency of Peruvian universities: A stochastic frontier analysis
Authors: Helena Veiga - UNED (Spain) [presenting]
Michael Wiper - Universidad Carlos III de Madrid (Spain)
Juan Carlos Orosco Gavilan - Universidad Carlos III de Madrid (Spain)
Abstract: Estimation of the one-sided error component in stochastic frontier models may erroneously attribute firm characteristics to inefficiency if heterogeneity is unaccounted for. We capture it through exogenous variables which may affect the location, scale, or both parameters of a truncated normal inefficiency distribution. The aim is to measure the efficiency of Peruvian universities via stochastic frontier analysis (SFA). The dataset is a panel of thirty-five Peruvian universities observed in the period 2011-2018. In the stochastic frontier, we have considered the number of students that ended the BA, the number of professors, the budget etc, letting for the inefficiency component the research activity measured by the number of papers published annually per professor, the region where the university is located and the ratio between executed and received budget. Our findings suggest that the inclusion of exogenous variables in the inefficiency distribution is able to capture university heterogeneity and helps to obtain more reliable efficiency scores and rankings.