|
|
Fit indices in complex survey data (T... |
|
Message/Author |
|
Sunny Shin posted on Thursday, December 09, 2010 - 9:09 am
|
|
|
Dear Linda and Bengt, I am running a series of unconditional and conditional growth curve models using the TYPE = COMPLEX RANDOM. I am also using the TSCORE command in conjunction with the previous code. Does MPLUS calculate fit indice (e.g., CFI, RMSEA) for these analyses? If not, is there a way to get these estimates via MPlus or otherwise? Thanks! |
|
|
Chi-square and related fit statistical are not defined in situations like yours where means, variances, and covariances are not sufficient statistics for model estimation. |
|
Sunny Shin posted on Thursday, December 09, 2010 - 12:19 pm
|
|
|
So there is absolutely no way to get these fit statistics. If situations are like this, what would you report in journal manuscript? AIC and BIC? Thanks. |
|
|
I would report BIC and I would also run neighboring, nested models and compare them via likelihood-ratio chi-square testing. |
|
Back to top |
|
|