Students receiving intelligent ITS feedback made significantly fewer errors in hypothesis-testing logic than students receiving verification feedback only¶

Claim · All claims
Evidence · 1 study · causal r2 · q3 · i1 small
Currency · newest study 2020 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i1 Experimental-group students made fewer different logic errors per solution (M=1.12, SD=0.79) than control-group students (M=1.42, SD=0.86), a significant difference with Cohen's d = 0.36. → Tacoma 2020

Evidence¶

Tacoma 2020¶

Tacoma, S., Heeren, B., Jeuring, J., & Drijvers, P. (2020). Intelligent Feedback on Hypothesis Testing. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-020-00218-y

q3 · i1 · causal · r2

Randomized controlled experiment embedded in a first-year psychology Methods and Statistics course, comparing an experimental group (N=163) receiving ITS feedback with a control group (N=151) receiving verification feedback. The experimental group made significantly fewer logic errors, with "Cohen’s d = 0.36".

"students in the experimental group made 1.12 (SD = 0.79) different errors per solution, while students in the control group made 1.42 (SD = 0.86) different errors, which was significantly more (t(312) = 3.22, p =. 0 0 1 , Cohen’s d = 0.36)"

Discussion¶

Related Claims¶

• Students receiving intelligent ITS feedback spent significantly more time and made significantly more steps on the hypothesis-testing tasks than controls — related
• Error rates per completed problem-solving step did not significantly differ between conditions — related
• Effects of intelligent ITS feedback did not transfer to follow-up hypothesis-testing tasks without intelligent feedback — related