Exploratory factor analysis in the pilot stage supported a four-factor solution, with three items removed (a weak loading, a cross-loading, and a low item–total correlation with duplicated content)¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Pilot EFA supported a four-factor solution and three items were removed: one for a weak primary loading (0.43), one for a cross-loading (0.52 and 0.39), and one for a low corrected item–total correlation (0.34) and content duplicating another item. → Fan Bu and Wei Li 2026

Evidence¶

Fan Bu and Wei Li 2026¶

Fan Bu and Wei Li (2026). Trust calibration and perceived developmental gains in university students' collaboration with generative AI: an exploratory sequential mixed methods study. Front. Psychol. 17:1861072. https://doi.org/10.3389/fpsyg.2026.1861072

q2 · i? · associational · r2

Pilot EFA (principal axis factoring with oblimin rotation) with an independent sample of 94 undergraduates from two universities outside the formal survey sample. The article reports the solution "supported a four-factor solution" and that removals left retained item loadings ranging from 0.58 to 0.83. Table 6 summarises the three removals as "for weak or ambiguous loadings", but the text gives a low item–total correlation and duplicated content, not a loading, as the reason for the third.

"The analyses supported a four-factor solution. Three items were removed. One contextual-support item had a weak primary loading of 0.43 and a communality of 0.36."

Discussion¶

Related Claims¶

• Exploratory factor analysis indicates a four-factor solution best fits the survey response data — related
• A four-factor principal component model of the MRBQ provides some empirical ground for the proposed structure of students' mathematics-related beliefs — related
• The adapted 15-item Internet Skills Scale replicates a three-factor structure (formal/navigation, informational/evaluation, operational) in Latin American college students — related
• Playful study design is measured as a two-dimensional construct of designing fun and designing competition, supported by exploratory and confirmatory factor analyses — related
• Exploratory factor analysis supports a five-factor GAA-LS structure explaining 67.82% of variance — related
• The 18-item PSRBVBQ yields a balanced three-factor structure (perceived severity, likelihood of responding to the bully, likelihood of responding to the victim) in Romanian middle school teachers — related
• Item-to-factor loading patterns qualitatively differ between human and LLM EFA solutions — related
• The MRIM scale has a three-factor structure of planning, monitoring, and evaluating of interactive metadiscourse, cross-validated by EFA and CFA — related
• Pilot testing found the initial problem posing test response time too short, with most pilot students unable to complete all three items — related
• A principal component analysis of the new cognitive load questionnaire yields a 15-item, three-component solution explaining 74.3% of total variance — related
• Children's scientific reasoning at the end of primary school has a three-component structure: Hypothesis validation, Experimentation, and Generating conclusions — related