.png){kind=icon}
.png){kind=icon}
Return
Bridging Theory and Simulation: Using ChatGPT for Computational Thinking Scale Replication Study
.png){kind=icon}
PRE
AI
DOI：10.1080/10447318.2025.2578402.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study evaluated the ability of ChatGPT to generate simulated data for theory replication and validation, focusing on the Computational Thinking Scale (CTS). The CTS model was replicated ten times, resulting in 10 trial models and 4,427 simulated responses. Each trial was analyzed using Structural Equation Modeling (SEM) to evaluate validity, reliability, and consistency. The results showed that ChatGPT-simulated data performed comparably to the original models. Key metrics-including Composite Reliability (simulated: 0.767-0.816; original: 0.84-0.88), Average Variance Extracted (simulated: 0.455-0.563; original: 0.57-0.67), Cronbach's Alpha (simulated: 0.595-0.702; original: 0.74-0.83), and R-squared (simulated: 0.215-0.33; original: 0.38-0.43)-were lower but aligned. Similar patterns were observed in structural path coefficients (simulated: 0.015-0.504; original: 0.20-0.43), further supporting comparability. These findings highlight the potential of ChatGPT as a generative tool for research simulations, enabling cost-effective, scalable methodological testing and a pathway for future investigation.
Keywords:
Theory validation
ChatGPT
replication study
simulation
computational thinking
Journal
I
IF:
4.9
Papers:
4.3K
Citations:
1.2W