Assessing the evidence for the comparability of socioeconomic status between students with and without immigrant background in Norway and Sweden

Large-scale Assessments in Education

An IERI – International Educational Research Institute Journal

Table 5 Likelihood-ratio tests and information criteria of the multi-group invariance models for Sweden

Model	LL	SCF	Npar	AIC	BIC	aBIC	Model comparisons
Model	LL	SCF	Npar	AIC	BIC	aBIC	cLRT	\(\Delta\) Npar	p
Model 1. Configural	− 78,166	1.158	194	156,720	157,997	157,380	–	–	–
Model 2. Metric	− 78,345	1.130	152	156,994	157,994	157,511	284.6	42	< .001
Model 3. Scalar	− 85,243	1.237	56	170,597	170,966	170,788	12,568.9	138	< .001
Measurement model for the total sample (N = 5336)	− 77,659	1.145	64	155,446	155,868	155,665	–	–	–
Measurement model for the native sample (n = 4244)	− 59,277	1.142	64	118,683	119,090	118,886	–	–	–
Measurement model for the 2ndGEN sample (n = 581)	− 7947	1.115	63	16,021	16,293	16,093	–	–	–
Measurement model for the 1stGEN sample (n = 511)	− 7457	1.166	64	15,042	15,311	15,108	–	–	–

LL: Log-likelihood value; Npar: Number of free parameters; SCF: Scaling correction factor; AIC: Akaike’s information criterion; BIC: Bayesian information criterion; aBIC: sample size adjusted BIC; cLRT: corrected Likelihood-ratio test statistic