Measurement invariance of the Hopkins Symptoms Checklist: a novel multigroup alignment analytic approach to a large epidemiological sample across eight conflict-affected districts from a nation-wide survey in Sri Lanka

Table 3 Fit statistics for invariance configural models tested using the alignment method across 8 conflict-affected districts

	Configural models	Alignment setting	No. of parameters	Log	AIC	BIC
1	Two-factor	Fixed	615	−18271.02	37772.04	42105.44
2	Three-factor	Fixed	623	−18901.53	39049.06	43438.93

Log loglikelihood, AIC Akaike, BIC Bayesian Information Criteria. Note: We tested a three-model based on the tripartite model proposed by Clark and Watson (1991) including the core constellations of anxiety-depressive symptoms and an additional domain of non-specific symptoms (insomnia, fatigue, restlessness, weakness, feeling tense). Models 1 and 2 tested using FREE method (all factor means were freely estimated) were poorly identified and therefore FIXED method (with Putalam fixed as the reference category) was used to estimate the model

ISSN: 1752-1505