Table 4. Measurement invariance across schizophrenia and other mental illnesses, and across genders.
Fit indices | ||||||
---|---|---|---|---|---|---|
Model | χ2 | df | P-value | RMSEA | CFI | SRMR |
Mental illness | ||||||
1M | 95.270 | 44 | < 0.01 | 0.0817 | 0.991 | 0.0282 |
2M | 97.693 | 50 | < 0.01 | 0.0735 | 0.991 | 0.0310 |
3M | 101.513 | 56 | < 0.01 | 0.0674 | 0.992 | 0.0314 |
4M | 101.889 | 59 | < 0.01 | 0.0637 | 0.992 | 0.0336 |
5M | 112.871 | 62 | < 0.01 | 0.0679 | 0.991 | 0.0318 |
Gender | ||||||
1G | 112.463 | 44 | < 0.01 | 0.0939 | 0.988 | 0.0222 |
2G | 121.201 | 50 | < 0.01 | 0.0885 | 0.987 | 0.0344 |
3G | 130.139 | 56 | < 0.01 | 0.0849 | 0.987 | 0.0330 |
4G | 132.598 | 59 | < 0.01 | 0.0823 | 0.987 | 0.0651 |
5G | 137.578 | 62 | < 0.01 | 0.0815 | 0.987 | 0.0653 |
Model 1M/1G: Configural model
Model 2M/2G: All first-order factor loadings were invariant between mental illnesses (2M) and genders (2G)
Model 3M/3G: All first-order factor loadings and item intercepts were invariant between mental illnesses (3M) and genders (3G)
Model 4M/4G: All first- and second-order factor loadings, and item intercepts were invariant between mental illnesses (4M) and genders (4G)
Model 5M/5G: All first- and second-order factor loadings, item intercepts, and construct means were invariant between mental illnesses (5M) and genders (5G)
df = degree of freedom; RMSEA = root mean square error of approximation; CFI = comparative fit index; SRMR = standardized root mean square residual; GFI = goodness of fit index; AGFI = adjusted goodness of fit index; AIC = Akaike’s information criterion; CAIC = consistent Akaike’s information criterion