2.3. Data Analysis

Descriptive analysis was carried out in each sample separately, using the statistics software, IBM SPSS 24 (IBM, Armonk, NY, USA). Pearson correlations were used to examine the interrelationships between variables. Cronbach’s alpha coefficient was calculated to test the reliability of each scale. Differences in the means of variables between the two groups were examined using the analysis of variance (t-test for independent samples). Psychometric properties of the scales were evaluated through a confirmatory factor analysis (maximum likelihood method of estimation) using Mplus 7 (Muthén & Muthén, Los Angeles, CA, USA) [34].

The multi-group structural equation model (SEM) was performed using Mplus 7 [34] to assess differences across both samples in the hypothesized model. The method of estimation was maximum likelihood (ML). According to the literature [35], the model was assessed using several goodness-of-fit criteria: The χ² goodness-of-fit statistic; the root mean square error of approximation (RMSEA); the comparative fit index (CFI); the Tucker Lewis index (TLI); and the standardized root mean square residual (SRMR). Non-significant values of χ² indicate that the hypothesized model fits the data. Values of RMSEA smaller than 0.05 indicate a good fit, values smaller than 0.08 indicate an acceptable fit, and values greater than 1 should lead to model rejection. CFI and TLI values greater than 0.95 indicate a good fit. The SRMR ranges from 0 to 1, with a cut-off criterion of 0.08, with higher values indicating an inferior fit to the empirical data and values lower than 0.05 indicating an excellent fit.

To address the common method variance issue, we performed the Harman’s single-factor test [36] using confirmatory factor analysis. Results indicate that one single factor could not account for the variance in the data, since all measures of goodness-of-fit show that the model did not fit the data (χ²(665) = 11,892.97, p < 0.01, RMSEA = 0.12 (90% confidence interval (CI) 0.11, 0.12), CFI = 0.53, TLI = 0.50, SRMR = 0.11); therefore, the threat of common method bias is unlikely.