Some theoretical questions about good... PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Konstantin posted on Wednesday, October 15, 2014 - 5:12 am
Dear friends, could you help me understand.
i have the next output

Chi-Square Test of Model Fit

Value 18.277
Degrees of Freedom 1
P-Value 0.0000


at the same time i have the next statistics
CFI/TLI

CFI 0.975
TLI 0.772



RMSEA (Root Mean Square Error Of Approximation)

Estimate 0.127
90 Percent C.I. 0.080 0.181
Probability RMSEA <= .05 0.004

Chi-Square Test of Model Fit tells me that is not good fit P<0,05
but clf =0,975 and RMSEA <0,05 that telles me about acceptable &#64257;t.

so what's true? why values of CLF and RMSEA CONFLICTING with p-level of chi-square
 Bengt O. Muthen posted on Wednesday, October 15, 2014 - 2:31 pm
CFI is often much friendlier than Chi-square and RMSEA. I would consider the sample size (which you don't give). If it is very large (several thousand cases) I can imagine going with CFI. At least if the correlations are not very low in which case CFI can mistakenly point to good fit.

I would also say that the chi-square and RMSEA results indicate that it is possible to modify your model to get better fit. You can check this out using Modindices.
 Konstantin posted on Thursday, October 16, 2014 - 2:24 am
yes i have big data set, more than 1000 observations
here its
https://www.sendspace.com/file/z4ayk4
i have uploaded on web share, cause i can't see how attache file here.
programm could work with variables
X4-X6
so they were excluded
 Bengt O. Muthen posted on Thursday, October 16, 2014 - 9:40 am
I have no more comment. We don't want to look at data via Mplus Discussion.
 Konstantin posted on Thursday, October 16, 2014 - 10:48 am
ooh i'm sorry. but can you help me if i got that result

DATA: FILE = "D:/2.dat";
VARIABLE: NAMES ARE y1 x1-x6;
MODEL: y1 ON x1-X6;

Observed dependent variables
Continuous
Y1

Observed independent variables
X1 X2 X3 X4 X5 X6


Estimator ML
Information matrix OBSERVED
Maximum number of iterations 1000
Convergence criterion 0.500D-04
Maximum number of steepest descent iterations 20

Input data file(s)
D:/2.dat

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

what means CFI=1 , is this pretty model or it some error?
 Bengt O. Muthen posted on Thursday, October 16, 2014 - 5:15 pm
It looks like you have a just-identified model, that is, zero degrees of freedom. This is the case for regression modeling. Such models do not give overall tests of model fit.

You will enjoy reading through one of the introductory SEM texts to get more familiar with these issues.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: