|
|
Chi-square value in small data set |
|
Message/Author |
|
|
Hi Dr. Muthen, I am running a model with sample size=200. The chi-square is significant but other fit indexes are quite acceptable. The sample size might not be the cause of the significance of because it is not large. Therefore the only reason I can figure out is that the assumption of data normality is invaded. Am I correct? If so, how can I test the normality of the data? Then what can I do to improve the model fit? Thanks. Malena |
|
|
Tests of normality are generally not reliable. I suggest running the model with a robust estimator and without to see if you get a difference. See Modification Indices for possible changes to improve model fit. Note that these changes should be substantively supported. |
|
Back to top |
|
|