Skip to main content

Table 3 Distribution of students' second-year outcomes across different predicted dropout risk intervals (2019)

From: Reducing dropout rate through a deep learning model for sustainable education: long-term tracking of learning outcomes of an undergraduate cohort from 2018 to 2021

Predicted dropout risk

20–30%

30–39%

40–49%

50–59%

60–69%

70–79%

Subtotal

p value*

Number of dropout students(%)

4(7%)

4(15%)

4(13%)

5(23%)

8(40%)

6(38%)

31(100%)

0.0044

Number of enrolled students(%)

55(93%)

23(85%)

28(88%)

17(77%)

12(60%)

10(63%)

145(100%)

  1. *Cochran–Mantel–Haenszel Statistics was used to test trend distribution in dropouts and Predicted risk levels. A two tailed p value < 0.05 was considered statistically significant