I have a three factor model which I am trying to fit for CFA using sem (n=79,407). The initial command is:
Here are portions of the output:
Running estat gof, stats(all), I get:
Why are the upper bound of RMSEA and pclose undefined?
Code:
sem (L1 -> x1 x3 x7 x13 x17)(L2 -> x2 x6 x9 x11 x15)(L3 -> x4 x5 x8 x10 x12 x14 x16), stand
Code:
Structural equation model Number of obs = 79,407 Estimation method = ml Log likelihood = -912300.53 ... LR test of model vs. saturated: chi2(116) = 34335.78, Prob > chi2 = 0.0000
Code:
---------------------------------------------------------------------------- Fit statistic | Value Description ---------------------+------------------------------------------------------ Likelihood ratio | chi2_ms(116) | 34335.782 model vs. saturated p > chi2 | 0.000 chi2_bs(136) | 451198.035 baseline vs. saturated p > chi2 | 0.000 ---------------------+------------------------------------------------------ Population error | RMSEA | 0.061 Root mean squared error of approximation 90% CI, lower bound | 0.000 upper bound | . pclose | . Probability RMSEA <= 0.05 ---------------------+------------------------------------------------------ Information criteria | AIC | 1.825e+06 Akaike's information criterion BIC | 1.825e+06 Bayesian information criterion ---------------------+------------------------------------------------------ Baseline comparison | CFI | 0.924 Comparative fit index TLI | 0.911 Tucker-Lewis index ---------------------+------------------------------------------------------ Size of residuals | SRMR | 0.049 Standardized root mean squared residual CD | 0.991 Coefficient of determination ----------------------------------------------------------------------------
Comment