**2. Methodology**

The purpose of this study was to examine if the academic performance of the first weeks is associated with the academic performance at the end of the academic period (16 weeks) in university students of the distance learning system of the Universidad Técnica Particular de Loja (UTPL) - a leading institution in distance learning in Ecuador. Academic performance is measured by the grades obtained by the students on a scale of zero to forty, with the possibility of accumulating ten

*Influence of Initial Study Activities on Final Academic Performance – An Analysis… DOI: http://dx.doi.org/10.5772/intechopen.99804*

points at each moment of measurement. The final AP was calculated as the sum of the four AP measurement moments. The results were taken by subject or course enrolled by the student.

Participants were (n = 6675) students from the April–August 2019 cohort, enrolled in 19 degrees or majors and 288 subjects or courses. With these data, 31928 enrollments per subject were generated, with a total of 127712 (31928 x 4) evaluation moments. The student population presented a heterogeneous profile in terms of personal, academic, socio-family, pedagogical and perhaps psychological characteristics. The information was taken from the academic records of each student, with the authorization of the Vice Rectorate of Open Modality of the University analyzed. At no time during the research were the personal data of the students used, guaranteeing the confidentiality of the participants.

To rule out systematic bias, comparative statistics of sample and cohort are presented. No systematic differences were found between sample and cohort. The average for the sample (n = 380 with 95% confidence) of students, taken at random, was 6.69 out of ten points in each event in which academic performance is measured, while for the population it was 6.59/10. In the sample the number of positive cases of passing the subject was 44.21%, while in the population it was 43.88%.

The analysis was carried out at two levels. The first was descriptive, using graphical tools and measures of central tendency; the second was inferential, calculating correlations, simple regression models and logit probability models.
