Longitudinal measurement invariance in urbanization index of Chinese communities across 2000 and 2015: a Bayesian approximate measurement invariance approach

Table 2 Fit indices of the Bayesian 1-factor and 2-factor EFA models of the Urbanicity Scale from 2000 to 2015

Year	N	Model	#	2.5% PPL	97.5% PPL	PPP	BIC	PP	RMSEA	CFI
2000	217	1-factor	36	19.4	80.8	0.002	10,277	0.9996	0.067	0.951
2000	217	2-factor	47	−17.4	53.7	0.157	10,293	0.0004	0.049	0.979
2004	216	1-factor	36	−6.9	59.4	0.052	10,428	1.0000	0.050	0.977
2004	216	2-factor	47	−22.8	41.3	0.272	10,460	0.0000	0.043	0.986
2006	218	1-factor	36	13.3	75.7	0.003	10,589	1.0000	0.063	0.963
2006	218	2-factor	47	−15.7	49.4	0.135	10,611	0.0000	0.055	0.976
2009	218	1-factor	36	16.4	79.2	0.002	10,580	1.0000	0.064	0.959
2009		2-factor	47	−12.7	53.1	0.119	10,603	0.0000	0.061	0.969
2011	290	1-factor	36	62.6	127.0	0.000	13,960	0.9598	0.069	0.945
2011	290	2-factor	47	14.8	81.3	0.004	13,967	0.0402	0.063	0.964
2015	288	1-factor	36	10.0	76.1	0.010	14,154	1.0000	0.054	0.962
2015	288	2-factor	47	−10.8	57.3	0.087	14,187	0.0000	0.047	0.971

EFA exploratory factor analysis, # number of free parameters, PPL posterior predictive limit, PPP posterior predictive p-value, BIC Bayesian information criterion, PP posterior probability, RMSEA root mean square error of approximation, CFI comparative fit index, TLI Tucker-Lewis index

ISSN: 1471-2458