Amos version 21

Propositions that link exogenous variables with endogenous variables were analyzed by structural equation modeling (SEM), which is reliable in examining the relationships between different constructs (i.e., differences among groups of latent variables), and provides accurate and meaningful results [27 (link)]. Compared with other techniques, it allows us to create several indicator variables (i.e., observable variables) per construct, which does not require the split analysis method and yields valid and clear inferences [28 (link)]. Therefore, the results of the relationships among variables are reliable and neutral [29 (link)]. Additionally, SEM has the capability to scrutinize complicated associations and a variety of hypotheses by simultaneously incorporating mean structures and group estimation [30 (link)]. Hence, the hypotheses proposed above were tested by structural equation modeling. Specifically, all data analyses were performed in two stages. First, this study employed SPSS version 25.0 (IBM Corporation: Armonk, NY, USA) to conduct evaluation of measured items’ stability and consistency by reliability analysis. Second, the assessment of the goodness-of-fit of the structural equation model and hypotheses testing were analyzed by moment structure through AMOS version 21.0 (IBM Corporation: Armonk, NY, USA).

Data analysis was performed using SPSS for Windows Version 20.0 (IBM, Inc., Armonk, NY, USA) and AMOS Version 21.0 (IBM, Inc., Armonk, NY, USA). The verification of the theoretical model was conducted in the two steps of measurement model analysis and structural model analysis. First, a confirmatory factor analysis was performed to test the measurement model. Factor loading, R², and construct reliability were used to evaluate reliability, and the average variance extracted was used as an indicator of validity. All of the measurement models and factor structure models (intrinsic motivations) should be supported by investigation data.
Next, all of the testing models were qualified, and further structural model analysis was carried out. The structural equation model (SEM) between variables was analyzed to verify the hypotheses. The goodness-of-fit of the model was evaluated using the chi-square test statistic, adjusted goodness-of-fit index (AGFI), standardized root mean square residual (SRMR), root mean square error of approximation (RMSEA), comparative fit index (CFI), and Tucker–Lewis index (TLI). Values that were higher than .90 for AGFI, CFI, and TLI or lower than .08 for RMSEA and SRMR indicated acceptable model fit (Hair, 2011 ).

We used SPSS version 21.0 (IBM Corp., Armonk, NY, USA) and AMOS version 21.0 (SPSS Inc., Chicago, IL, USA) to analyze our data. Structural equation modeling was used to test model fit. In this study, the model fit was examined using chi-square (χ²), goodness of fit index (GFI), adjusted goodness of fit index (AGFI), and the root mean square error of approximation (RMSEA). A χ² value without significance, GFI and AGFI greater than 0.90, and RMSEA less than 0.05 indicated a good model fit. The Sobel test is a method of testing the significance of a mediation effect, and a Z value ≧ 1.96 showed that meditation might exist [24 ].

All data were analyzed using SPSS version 21.0 for Windows (IBM Corp., Armonk, NY, USA) and AMOS version 21.0 (SPSS Inc., Chicago, IL, USA). The CFS, Barthel Index, SPMSQ, and GDS-SF data were subjected to descriptive statistics, including analyses of frequency, percentage, range, mean, and standard deviation. Bivariate correlations were used to examine the relationships between variables. For data analysis and hypothesis testing, a confirmatory factor analysis of the initial measurement model and the maximum likelihood method were used for data fitting. Structural equation modeling (SEM) was used to test model fit. The model fit was examined using chi-square/df (χ2/df), goodness of fit index (GFI), adjusted GFI (AGFI), and the root mean square error of approximation (RMSEA). A good model fit is indicated by a non-significant χ2 /df value, GFI and AGFI greater than 0.90, and an RMSEA of less than 0.05. The Sobel test is a method of testing the significance of a mediation effect. The Sobel test is a z test, in which a z value ≥1.96 suggests that meditation may exist [28 (link)].

The original EFA was performed using IBM SPSS version 19 and the follow-on CFA was performed using Mplus Version 7.11 Muthen & Muthen. The path diagram was created with IBM AMOS version 21 which was also used as a sensitivity analysis for replicating the analysis and for measuring measurement invariance with an ML estimator.