TABLE 1.

Summary of fit indices and the desired outputs in mediation analysis

Fit index	What is measured	Rule(s) of fit
χ2	Determines the magnitude of discrepancy between the covariance matrix estimated by the model and the observed covariance matrix of the data sets	Should be nonsignificant, meaning the estimated covariates are not significantly different from the actual data covariates
Comparative fit index (CFI)	Determines if the model fits the data by comparing the χ2 of the model with the χ2 of the null model; adjusts for sample size and no. of variables	>0.90, acceptable; >0.95, good
Root mean square error of approximation (RMSEA)	Determines how well the model fit the data and favor parsimony and a model with fewer parameters	<0.05 to 0.06, good; 0.06 to 0.08, acceptable; 0.08 to 0.10, mediocre; >0.10, unacceptable
Standardized root mean square residual (SRMR)	A standardized square-root of the difference between the observed correlation and the predicted correlation	< 0.05, good; 0.05 to 0.08, acceptable; 0.08 to 0.10, mediocre; >0.10, unacceptable
Akaike information criterion (AIC)	Determines if one model fits the data better than the other	The lower value is preferred when comparing two model estimations from the same data set
Baysian information criterion (BIC)	Determines if one model fits the data better than the other; while AIC has a penalty of 2 for every estimated variable, the BIC penalty increases with an increase in sample size	The lower value is preferred when comparing two model estimations from the same data set
Tucker Lewis index (TLI)	Determines to what extent the model of the interest improves the fit compared to the fit of the null model	TLI ≥ 0.95