AI supported education technology and academic achievement of students

Last registered on September 06, 2021

Pre-Trial

Trial Information

General Information

Title
AI supported education technology and academic achievement of students
RCT ID
AEARCTR-0008188
Initial registration date
September 04, 2021
Last updated
September 06, 2021, 2:18 PM EDT

Locations

Region

Primary Investigator

Affiliation
Peking University

Other Primary Investigator(s)

PI Affiliation
Peking University
PI Affiliation
Peking University
PI Affiliation
iFLYTEK

Additional Trial Information

Status
In development
Start date
2021-09-20
End date
2022-01-31
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
Abstract
This research targets on evaluating the causal impact of AI supported education technology on academic achievement of students, by conducting large-scale Randomized Controlled Trials (RCT) in multiple middle schools in various cities in China.
External Link(s)

Registration Citation

Citation
Liu, Chenran et al. 2021. "AI supported education technology and academic achievement of students." AEA RCT Registry. September 06. https://doi.org/10.1257/rct.8188-1.0
Experimental Details

Interventions

Intervention(s)
Intervention Start Date
2021-09-27
Intervention End Date
2021-12-31

Primary Outcomes

Primary Outcomes (end points)
Academic achievement of students measured by exam scores.
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
We first recruit middle schools to participate in our experiment around China, with the help of the iFLYTEK. In each recruited school, we then randomly several classes in the 7th grade into treatment group and some other classes in the same grade into control group.

For the treatment group, each student is arranged to use an AI learning device provided by the iFLYTEK to do math exercises. The device is designed to be capable of providing adaptive exercises to the user’s mastery of learning materials, and to help the user finally grasp all key points of the course. This feature is achieved by taking advantage of massive question database, AI algorithm and cloud computing technology. Except for this, all other schedule and arrangement of teaching and learning remain unchanged.

For the control group, we do not make any interferences.
Experimental Design Details
Not available
Randomization Method
Randomization done in office by a computer.
Randomization Unit
Class.
Was the treatment clustered?
Yes

Experiment Characteristics

Sample size: planned number of clusters
About 200 classes.
Sample size: planned number of observations
About 10000 students.
Sample size (or number of clusters) by treatment arms
100 classes control, 100 classes provided with the AI learning devices.
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
IRB

Institutional Review Boards (IRBs)

IRB Name
Institutional Review Board, Guanghua School of Management, Peking University
IRB Approval Date
2021-09-04
IRB Approval Number
#2021-28