Validation of a short form Wisconsin Upper Respiratory Symptom Survey (WURSS-21)

Table 5 Model fit Exploratory Factor Analysis for WURSS-44 using 3 to 10 dimensions

Dimensions	Chi-square	df	χ²/df	CFI	TLI	RMSEA	SRMR
3	6902.7	738	9.35	.974	.970	.192	.076
4	5114.1	699	7.31	.982	.977	.167	.061
5	3946.8	661	5.97	.986	.982	.148	.050
6	2922.0	624	4.68	.990	.987	.127	.041
7r	2054.4	489	4.20	.993	.989	.119	.034
8	1785.5	553	3.22	.995	.992	.099	.029
8r	1625.9	457	3.55	.995	.992	.106	.028
9	1430.5	519	2.75	.996	.994	.088	.024
10	1165.6	486	2.39	.997	.995	.078	.021

7r and 8r = Dimensions restricted to exclude headache, loss of appetite, and sleep well,
items which did not
CFI = Comparative Fit Index
TLI = Tuker-Lewis Index
RMSEA = Root Mean Square Error of Approximation
SRMR = Standardized Root Mean Square Residual
Hu and Bentler (1999)[58] suggest the following cut off values for good fit, CFI > .95, TLI > .95, RMSEA < .06, and SRMR < .08

ISSN: 1477-7525