Table 3.
Model fit statistics.a
Model | Chi-square (df) | χ2/df | RMSEAb | CFIc | SRMRd | ||||||
Measurement model |
|
|
|
|
|
||||||
|
Model 1: Baseline (2-factor)e | 1149.1 (303) | 3.79 | 0.072 | 0.86 | 0.059 | |||||
|
Model 2. Revised (3-factor)f | 904.8 (296) | 3.06 | 0.062 | 0.90 | 0.052 | |||||
|
Model 3: Revised + correlated error | 638.0 (290) | 2.20 | 0.047 | 0.94 | 0.049 | |||||
Structural model |
|
|
|
|
|
||||||
|
Model 1: Baseline conceptual | 923.0 (343) | 2.69 | 0.056 | 0.91 | 0.081 | |||||
|
Model 2: Revised | 931.7 (351) | 2.65 | 0.055 | 0.91 | 0.083 |
aRecommended cutoff points for model fit indices [46-48]: SRMR of <0.08; RMSEA of <0.08; CFI of >0.90 (ideally CFI of ≥0.95); χ2/df of <3. Hu and Bentler [47] suggest a 2-index presentation strategy, recommending a RMSEA of 0.06 or lower and a SRMR of 0.09 or lower.
bRMSEA: root mean square error of approximation.
cCFI: comparative fit index.
dSRMR: standardized root mean residual.
e2-factor: active seeking and scanning channels.
f3-factor: searching, browsing, and scanning channels.