Language Testing in Asia

Table 3 Goodness-of-fit indices of the four hypothesized models

From: Assessing the content typicality and construct of Persian language proficiency test (PLPT) for non-Persian speakers: a corpus-informed study

Model	Fit statistics
Model	χ²	df	CMIN/DF ( 1>, 3<)	CFI (≥.90)	GFI (≥.90)	RMSEA (≤.08)	AIC (the lower)	BIC (the lower)	p-close
Sample 1
Unitary	95.68	53	1.7	.88	.79	.15	143.68	193.94	.006
Higher-order	86.70	52	1.6	.89	.89	.08	136.70	189.06	.022
Uncorrelated	94.53	53	1.7	.77	.81	.11	142.53	192.80	.007
Correlated	45.61	52	1.5	.91	.91	.07	124.88	168.86	.70
Sample 2
Unitary	78.62	53	1.4	.86	.86	.05	108.62	158.88	.52
Higher-order	76.07	52	1.4	.89	.89	.08	124.07	174.33	.90
Uncorrelated	86.62	53	1.6	.79	.82	.09	126.42	168.31	.89
Correlated	65.61	52	1.2	.90	.91	.05	111.61	158.90	.71

Df/DF degrees of freedom, χ²/CMIN chi-square, CMIN/DF χ²/df

Back to article page