Tests | PS (RM) | PS (GLLRM)a | LPS (RM) | LPS (GLLRM)b |
---|
CLR | Df | p | CLR | df | p | CLR | Df | p | CLR | df | p |
---|
Global homogeneity | 13.1 | 8 | .11 | 15.4 | 15 | .43 | 14.6 | 6 | .02+++ | 10.3 | 9 | .32 |
DIF relative to: |
Child sample | 106.0 | 8 | <.0005+ | 16.4 | 11 | .16 | 44.2 | 6 | <.0005+++ | 22.7 | 7 | <.01++++ |
Children age group | 45.5 | 16 | <.0005+ | 47.8 | 30 | .02++ | 42.1 | 12 | <.0005+++ | 33.7 | 18 | .01++++ |
Parent | 10.1 | 8 | .26 | 18.8 | 15 | .22 | 8.4 | 6 | .21 | 11.0 | 9 | .27 |
Parent education | 73.6 | 8 | <.0005+ | 17.5 | 9 | .04++ | 17.9 | 6 | <.01+++ | 18.7 | 9 | .03++++ |
Parent age group | 22.1 | 16 | .14 | 51.9 | 30 | <.01++ | 24.5 | 12 | .02+++ | 28.5 | 18 | .05 |
- Notes. PS Parental stress, LPS Lack of parental satisfaction, RM Rasch model, GLLRM Graphical loglinear Rasch model, CLR Conditional likelihood ratio, df degrees of freedom, p p-value, DIF differential item function
- Global homogeneity test compares items parameters in approximately equal-sized groups of high and low scoring parents. The critical limits for the p-values after adjusting for false discovery rate were: + 5% limit p = .0083, 1% limit p = .0017. ++ 5% limit p = .008. +++ 5% limit unaltered, 1% limit p = .0017. ++++ 5% limit p = .0083, 1% limit p = .0017
- aThe GLLRM for the Parental Stress subscale assumed that some items pairs are locally dependent (items 3 and 4, and items 9 and 12), that item 9 and 13 functions differentially relative to child sample, and that item 4, 15 and 16 functions differentially relative to parent educational level
- bThe GLLRM for the Lack of Parental Stress subscale assumed that items 1 and 6, and items 1 and 17 are locally dependent and that item 1 functions differentially relative to child sample