Internet Learning Volume 3, Number 2, Fall 2014 | Page 62

Using Early Warning Signs to Predict Academic Risk in Interactive, Blended Teaching Environments
Table 1. Regression models predicting final course grades
CSEM
score
Selfefficacy
(pretest)
Peerinstruction
selfefficacy
(pretest)
Early
Learning
Catalytics
responses
Early
problem
sets
Model
1
Model
2
Model
3
Model
4
Model
5
Model
6
Model
7
Model
8
0.24*** 0.20*** 0.20*** 0.17*** 0.14** 0.07 0.04 0.04
2.89* 3.34* 2.14 3.39** 2.41* 0.92 0.40
-1.11
0.33**
0.83*** 0.57** 0.34* 0.30*
Midterm 1 0.64** 0.31 0.30
Midterm 2 0.81*** 0.73***
Midterm 3 0.18*
R 2 0.29 0.34 0.35 0.42 0.53 0.60 0.75 0.77
RMSE 6.9 6.7 6.7 6.3 5.7 5.3 4.3 4.1
* p < 0.05, ** p < 0.01, *** p < 0.001
61