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

Table 6 Results of approximate metric invariance model with prior variance of 0.01 for the differences in factor loadings of the Urbanicity Scale from 2004 to 2011

Item	λ		Deviations from the average λ				Δ
Item	Average	SD	2004	2006	2009	2011	Δ
Communication	1.12	0.07	0.01	− 0.04	− 0.01	0.04	7.4%
Population density	1.05	0.08	−0.02	− 0.04	0.02	0.04	7.0%
Diversity	0.86	0.06	0.03	0.04	−0.06*	− 0.01	12.1%
Economic activity	2.31	0.13	0.02	−0.02	0.04	−0.04	3.6%
Health structure	1.28	0.11	0.05	0.05	−0.02	−0.08	10.3%
Housing	1.75	0.09	0.17*	0.08*	−0.05	− 0.20*	21.0%
Traditional market	2.07	0.16	−0.01	0.04	0.01	−0.04	3.9%
Social services	1.66	0.12	0.01	−0.03	0.01	0.02	3.0%
Transportation	1.06	0.10	−0.01	0.03	0.00	−0.01	3.6%
Education	1.27	0.09	−0.14*	0.02	−0.03	0.15*	22.2%
Modern market	2.11	0.13	0.02	0.01	−0.03	0.00	2.0%
Sanitation	2.35	0.13	0.02	0.04	0.02	−0.08	4.9%

* p < 0.05; λ = factor loading; SD standard deviation; Δ = maximum proportional deviation from the average loading across the 2004–2011 waves. The top two significant deviations from the average loading are highlighted in bold

ISSN: 1471-2458