Socioeconomic and attitudinal differences between service users of private and public early childhood education and care in the Finnish context

International Journal of Child Care and Education Policy

Table 8 Invariance tests of the dimensions of attitudes towards ECEC and its provision

Invariance step		χ² value	df	Scaling correction	χ² difference test^a	CFI	ΔCFI	TLI	ΔTLI	RMSEA (90% CI)	ΔRMSEA	SRMR	ΔSRMR
1	Weak invariance (loadings)	468.41	203	1.06	–	0.925	–	0.899	–	0.053 (0.047–0.059)	–	0.047	–
2	Strong invariance (loadings, intercepts)	506.94	223	1.06	Model 2 vs. 1 Δχ² = 38.70**	0.92	0.005	0.902	− 0.003	0.052 (0.046–0.058)	0.001	0.05	− 0.003
3	Strict Invariance (loadings, intercepts, residual variances)	595.42	251	1.08	Model 3 vs. 2 Δχ² = 86.39***	0.903	0.017	0.894	0.008	0.054 (0.049–0.06)	− 0.002	0.069	− 0.019
3p	P. strict variance (loadings, intercepts, residual variances)	561.85	249	1.08	Model 3p vs. 2 Δχ² = 55.23***	0.911	0.009	0.903	− 0.001	0.052 (0.046–0.058)	0	0.06	− 0.01
4	Loadings, intercepts, residual variances (p), factor variances and covariances	620.81	269	1.08	Model 4 vs. 3p Δχ² = 58.16***	0.9	0.011	0.899	0.004	0.053 (0.047–0.058)	− 0.001	0.09	− 0.03

p partial invariance
^aA stricter model fits the data better if p < 0.05, if ΔCFI ≤ 0.01, ΔTLI ≤ 0.01 and ΔRMSEA ≤ 0.015. **p < 0.01, ***p < 0.001. Δ = change