Table 5.

Model goodness-of-fit comparison between latent variable SEM and repeated measures ANOVA approach of Faecalibacterium based on four measurements (Sanger, 454 pyrosequencing V1V3, 454 pyrosequencing V3V5 and qPCR)

MODEL	MODEL CONSTRAINT	GOODNESS-OF-FIT
A: Latent variable SEM	set only λ1 = 1	Chi-square	5.089 (df = 2) Pr > χ2: 0.079
		RMSEA	0.105
		CFI	0.994
B: Equivalent to repeated measures ANOVA (multivariate approach)	set all indicator path coefficient λi ≡ 1 (i = 1, 2, 3, 4)	Chi-square	129.955 (df = 5) Pr > χ2: < .001
		RMSEA	0.421
		CFI	0.750
C: Equivalent to repeated measures ANOVA (univariate approach)	set all indicator path coefficient λi ≡ 1; set all indicator error variances to be equal, var (εi) ≡ σ2 (i = 1, 2, 3, 4)	Chi-square	172.068 (df = 8) Pr > χ2: < .001
		RMSEA	0.381
		CFI	0.671