Psychometric properties of a short version of the questionnaire on factors influencing degree completion among Peruvian graduate students

Raffo Ibarra G.A.; Lozano Lozano M.; Herrera Alvarez A.M.; Baldeón De La Cruz M.D. · Frontiers in Education (2026) · DOI: 10.3389/feduc.2026.1887990

Resumen

Graduate degree completion remains a major concern for higher education institutions due to its implications for academic quality, student retention, and institutional efficiency. There is a growing interest in understanding the factors associated with delayed graduation; however, evidence regarding the psychometric robustness of instruments assessing these factors in Latin American contexts is still limited. This study aimed to evaluate the internal structure and reliability of the short version of a questionnaire designed to assess factors influencing degree completion among Peruvian graduate students. A sample of 363 graduate students from a private university in Lima participated in the study. Item analysis, exploratory and confirmatory factor analyses, as well as reliability estimation, and measurement invariance procedures were conducted. The findings revealed substantial psychometric limitations, including non-normal item distributions, weak item discrimination in several indicators, and inadequate global fit for the proposed four-factor correlated model estimated via WLSMV [χ²(2, 768) = 12, 046, CFI = .725, TLI = .716, RMSEA = .096, SRMR = .187]. While overall reliability based on Cronbach's alpha was satisfactory, the hierarchical omega values (ranging from.41 to.68) and low AVE estimates indicated that the multidimensionality and error variance compromised the internal structural validity of the 80-item version. These findings highlight the challenges of adapting instruments related to graduate degree completion across sociocultural contexts and underscore the need for further theoretical and psychometric refinement.

Instituciones: Universidad Privada Norbert Wiener