Psychometric properties of the Greek translation of the Friendship Quality Questionnaire

Abstract

The present study examines the psychometric properties of the long form (LF) of the Greek translation of the Friendship Quality Questionnaire (FQQ), a widely recognized self‐report instrument that assesses children's perceptions of the qualities of their friendships. Four hundred seventeen (417) typically developing primary‐school students (50.8% boys), aged between 8 and 12 years (M = 9.77 years old, SD = 1.2), who had a mutual best friend in their class, completed the survey at school. Confirmatory factor analysis verified the six‐factor structure of the original FQQ with all items fitting into the respective subscales. All factors presented high positive intercorrelations except for the Conflict and Betrayal subscale. All subscales demonstrated adequate internal consistency. Significant gender differences were observed. The Greek translation of the FQQ‐LF shows strong evidence of validity and reliability and provides a suitable instrument for assessing the qualitative characteristics of best friendships.

Exploring the psychometric properties of the French revised test anxiety + regulatory scale in Swiss secondary school students

“…These authors demonstrate that AVE is highly sensitive to models with high factor loadings and high factor loadings heterogeneity (i.e., high standard deviation of average factor loadings), while CR is sensitive to models with more than 10 items. The commonly accepted thresholds for CR (i.e., ≥0.70) and AVE (i.e., ≥0.50) were therefore adjusted accordingly, and analyzed in conjunction with the standard error of measurement (SEM < SD/2; e.g., Kouvava et al, 2022). Cronbach's alpha and McDonald's omega coefficients, as well as correlations between the FRTA + R factors were also observed.…”

“…Another aim is to test the factorial invariance of the scale across gender and grade levels in order to compare latent means. Latent mean comparison analysis is more powerful and outperforms traditional techniques of comparison by providing more accurate results and less biased mean estimations (Chen et al, 2019;Kouvava et al, 2022). Grade level was preferred to age since Mascret et al (2021) had found no significant results for the predictive role of age in a large sample of French students.…”

“…α, Cronbach's alpha; ω, McDonald's omega; SEM, standard error of measurement (calculated by multiplying the standard deviation of the factor by the square root of one minus the omega coefficient of the factor; e.g.,Kouvava et al, 2022); AVE, average variance extracted; diagonal elements in bold represent the square root of the AVE for each factor. *p < 0.05, **p < 0.01, and ***p < 0.001.…”