Message/Author 

MBH posted on Monday, March 31, 2014  5:12 pm



Dear Linda and Bengt, I'm running a CFA prior to running SEM. I've constructed a CFA of 3 variables and here are the model fit information I'm getting: RMSEA (Root Mean Square Error Of Approximation) Estimate 0.000 90 Percent C.I. 0.000 0.000 Probability RMSEA <= .05 0.000 CFI/TLI CFI 1.000 TLI 1.000 ChiSquare Test of Model Fit for the Baseline Model Value 15690.622 Degrees of Freedom 3 PValue 0.0000 WRMR (Weighted Root Mean Square Residual) Value 0.006 Does the statistics above mean that the model is a perfect fit to be included subsequently in the SEM? I've been reading that CFI should be below 1.00 and be between 0.901.00 and not be exactly 1.00. Thanks for your help. 


A factor with three indicators is just identified. Fit cannot be assessed. The model has no degrees of freedom. 

MBH posted on Monday, March 31, 2014  6:13 pm



Thanks for the quick reply. So this means that the factor cannot be included in further analysis for SEM? 


You can include it. It will affect the fit of the total model. 

MBH posted on Monday, March 31, 2014  6:42 pm



Dear Bengt, That's what I thought. But in situations like this, it is arbitrary to either include it or not to include it? 


It is your decision whether you want it in the model. 

Back to top 