Patient preference for involvement, experienced involvement, decisional conflict, and satisfaction with physician: a structural equation model test

Table 5 Global goodness-of-fit indexes

	Χ²	df	p	Χ²/d.f.	RMSEA	TLI	CFI
Recommendation for good fit				<2.0	< 0.05	≥ 0.95	≥ 0.95
Recommendation for acceptable fit				<5.0	<0.08	≥ 0.90	≥ 0.90
Model development
Step 1	5,594.09	1,346	<.001	4.156	0.057	0.860	0.878
Full path model	5,594.09	1,346	<.001	4.156	0.057	0.860	0.878
Step 2	5,686.63	1,386	<.001	4.103	0.056	0.862	0.876
Correlations <0.1 removed	5,686.63	1,386	<.001	4.103	0.056	0.862	0.876
Step 3	5,691.09	1,387	<.001	4.103	0.056	0.862	0.876
Correlations <0.1 removed	5,691.09	1,387	<.001	4.103	0.056	0.862	0.876
Step 4	5,746.15	1,414	<.001	4.064	0.056	0.864	0.875
Causal associations <0.1 removed	5,746.15	1,414	<.001	4.064	0.056	0.864	0.875
Step 5	5,749.91	1,415	<.001	4.064	0.056	0.864	0.875
Causal associations <0.1 removed	5,749.91	1,415	<.001	4.064	0.056	0.864	0.875
Final model	5,271.38	1,066	<.001	4.945	0.063	0.863	0.876
Redundant variables removed	5,271.38	1,066	<.001	4.945	0.063	0.863	0.876
Confirmatory testing
Final model	5,064.57	1,066	<.001	4.751	0.064	0.860	0.873

Df degrees of freedom, RMSEA Root Mean Square Error of Approximation, TLI Tucker-Lewis Index, NFI Normed Fit Index; recommendations are based on: [20, 23, 24, 27, 28].

ISSN: 1472-6963