Model | χ^{2} (*df*) | CFI | RMSEA [90% CI] | SRMR | Model comparison | Decision |
---|

Ref. | Δ*χ*^{2} (Δ*df*) | ΔCFI | ΔRMSEA | ΔSRMR |
---|

CFA 1: Full scale | 103.58* (35) | 0.993 | 0.044 [0.034, 0.054] | 0.048 | - | - | - | - | - | Accept |

CFA 2: Short scale | 4.34 (2) | 0.999 | 0.034 [0.000, 0.078] | 0.022 | - | - | - | - | - | Accept |

Invariance |

MI 1: configural | 185.20* (70) | 0.996 | 0.035 [0.029, 0.041] | 0.036 | - | - | - | - | - | Accept |

MI 2: metric | 603.73* (79) | 0.981 | 0.070 [0.065, 0.076] | 0.064 | MI 1 | 418.53* (9) | 0.015 | 0.035 | 0.028 | Reject |

MI 2a: partial metric | 431.67* (78) | 0.987 | 0.058 [0.053, 0.064] | 0.054 | MI 1 | 246.47* (8) | 0.009 | 0.023 | 0.018 | Accept |

MI 3: scalar | 1331.43* (87) | 0.954 | 0.103 [0.099, 0.108] | 0.088 | MI 2a | 899.76* (9) | 0.033 | 0.045 | 0.034 | Reject |

MI 3a: partial scalar | 593.78* (84) | 0.981 | 0.067 [0.062, 0.072] | 0.061 | MI 2a | 162.11* (6) | 0.006 | 0.009 | 0.007 | Accept |

MI 4: residual | 682.74* (94) | 0.978 | 0.068 [0.064, 0.073] | 0.067 | MI 3a | 88.96* (10) | 0.003 | 0.001 | 0.006 | Accept |

- Note. CFA:
*N* = 1025; MI: *n*_{1} = 1025; *n*_{2} = 1654. We did not consider the *χ*^{2} test for model rejection, because its sensitivity increases with sample size: In large samples—as is the case in this study—even small model–data discrepancies produce significant results (Bollen & Long, 1993; Cheung & Rensvold, 2002) *CFI* comparative fit index, *RMSEA* Root Mean Square Error of Approximation, *SRMR* Standardized Root Mean-square Residual, *Ref.* reference model- *
*p* < 0.001