Examples of SRMR in a sentence
The CFI (.97), NNFI (.96), SRMR (.069), and RMSEA (.058) fit statistics were adequate but not better than those obtained from the 52-item ten-factor solution.Overall, the best fitting model for this data was a 52-item ten-correlated factor model representing CONF_P, CONF_N, USE_P, USE_N, IMP, LIKE, ANX_P, ANX_N, MATBEHA, and TIME, but with LIKE5 and ANX2removed from the respective scales.
After adjusting the measurement model, the structural model for model 16 (see figure 3: χ²(1341, N=520) = 2393.11; CFI = 0.909; TLI = 0.900; RMSEA = 0.039, [0.036 ; 0.041]; SRMR = 0.063; AIC = 70067.49; BIC = 71147.97) showedacceptable fit.
The baseline model had the following fit statistics: χ2 =1799.039 with p < .001; CFI = 0.888; RMSEA = 0.080; and SRMR = 0.055.
All four main measures and indexes used to evaluate a model’s good fit or goodness-to-fit were met (CFI, TLI, RMSEA and SRMR).
Standardized Root Mean Square Residual [SRMR] measures the average standardized difference between the observed and predicted correlations.
Additionally, the SRMR statistics need to be lower than0.08 to confirm that the proposed model fits the data [60,61].
When these values are compared with the normality values of the goodness of fit indices specified in Table 2, it is seen that χ2 / df, RMSEA, and SRMR values show perfect fit, and the GFI value shows a good fit.
Good criteria for measurement model fit are CFI greater than 0.95, SRMR less than 0.08, and RMSEA less than 0.06 (Hu and Bentler 1999).
We made use of common methods, such as the R2 coefficient and thestandardised root mean squared residual (SRMR) score, to evaluate the model's predictive accuracy indicators.
SRMR- Standardized Root Mean Square Residual ACKNOWLEDGEMENTSThe College of Medicine and Research Center (CMRC) of the King Saud University.