Study of performance in first year subjects and the impact on evasion and remaining time of students in UNICAMP exact courses

Abstract

This project aims to measure the impact of performance in compulsory subjects in the first year of graduation, the performance of entrance exams and the candidate's socioeconomic profile, on evasion and length of stay in the exact, technological and earth science courses at Unicamp, using data for entering students via entrance exam in the period from 2012 to 2018. For this, the following will be proposed: 1) a logistic regression model to estimate the probability of a student dropping out; and 2) a proportional hazards model with competitive risks to characterize the student's length of stay at the university, taking into account two possible outcomes: course completion and dropout. Length of stay will be measured as the number of semesters of admission student output, therefore being a discrete variable. (AU)