Pairwise statistical tests confirm random forest's performance differences from other models are statistically significant (p < 0.05)¶

Claim · All claims
Evidence · 1 study · associational r1 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? Welch's t-tests and Mann–Whitney U tests on 30 independent runs produced p-values below 0.05 in all pairwise comparisons among GRU, LSTM, logistic regression, transformer, and random forest. → Lala Yamazaki and Ramchandra Rimal 2026

Evidence¶

Lala Yamazaki and Ramchandra Rimal 2026¶

Lala Yamazaki and Ramchandra Rimal. (2026). Leveraging Physiological Signals to Predict Exam Outcomes with Machine Learning. https://arxiv.org/abs/2606.14960 doi:10.48550/arxiv.2606.14960

q2 · i? · associational · r1

Statistical analysis of 30 independent test runs per model (SVM excluded for deterministic outputs); the article reports p-values "below the 0.05 significance level in all pairwise comparisons", supporting random forest's superiority. Normality was checked with the D'Agostino and Pearson omnibus test.

"The t-tests and Mann–Whitney U tests produced p-values below the 0.05 significance level in all pairwise comparisons, confirming that the observed performance differences were statistically significant and not likely due to chance."

Discussion¶

Related Claims¶

• Deep learning models (LSTM, GRU, transformer) achieve high and comparable accuracy (0.90–0.93) on physiological exam-outcome prediction — reports the opposite
• Random forest achieves the highest mean test accuracy (0.9590) of all models compared for predicting exam grade categories from physiological signals — related
• In the random forest, word count was the most important readability feature while traditional readability formulas ranked near the bottom — related
• Logistic regression performs poorly (mean accuracy 0.4243) and SVM moderately (0.7374) on physiological exam-outcome prediction — related