|
Message/Author |
|
Anonymous posted on Wednesday, April 20, 2005 - 6:46 am
|
|
|
Hello I have made a CFA to compare the fit os different factor structures of a General Health Questionnaire. The proposed models are one factor, two factor or three factor models. The questions to the test are coded in a binary variable so I used the WLSMV estimator. The 'problem' I got is that the fit indices are almost the same for every model: Proposed models CFI NNFI RMSEA chi/d.f Unidimensional 0.99 0.99 0.048 75.43/54 Politi 0.99 0.99 0.049 72.21/52 Andrich 0.99 0.99 0.049 72.40/53 Schmitz 0.99 0.99 0.052 62.42/43 Graetz 0.99 0.99 0.046 69.27/51 Martin 0.99 0.99 0.048 74.48/51 Worsley 0.99 0.99 0.046 70.68/51 Farrell 0.99 0.99 0.048 67.73/51 Is that homogeneity indicating me that all the models fits the data equally well/bad? Thank you |
|
BMuthen posted on Wednesday, April 20, 2005 - 9:29 am
|
|
|
Yes, it looks like the models fit the data about the same. |
|
Back to top |
|
|