Prior programming experience significantly predicted Promptly task performance and prompting self-efficacy¶

Claim · All claims
Evidence · 1 study · causal r2 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Prior programming experience was a significant predictor of task performance (B = 0.563, p = 0.021) and of prompting self-efficacy (B = 1.178, p < 0.001) in the mixed-effects models. → Keith Tran 2026

Evidence¶

Keith Tran 2026¶

Keith Tran, Samiha Marwan, and Thomas Price. (2026). Teaching Prompt-Based Programming with LLMs: A 45-Minute Lesson with Guided Practice for End-User Programmers. https://arxiv.org/abs/2606.30547 doi:10.48550/arxiv.2606.30547

q3 · i? · causal · r2

Covariate analysis within the same randomized controlled study's linear mixed-effects models; experience was a composite of prior courses, programming frequency, and self-assessed comfort, and was also a significant self-efficacy predictor consistent with prior work.

"Prior Programming Experience was a significant predictor of performance (𝐵 = 0.563, 95% CI[0.085, 1.042],𝑝 = 0.021), estimating that each standard deviation of additional experience corresponded to 0.56 more problems solved."

Discussion¶

Related Claims¶

• Metacognitive strategies and prior coding experience significantly predict CT profile membership, with metacognition contributing more strongly — related
• The 45-minute prompting lesson significantly increased prompting self-efficacy relative to a business-as-usual control lesson — related
• A 45-minute prompt-based programming lesson produced greater pre-to-post gains in Promptly problem solving than a code-tracing control, though not statistically significant — related