Using the Standardized Root Mean Squared Residual (SRMR) to Assess Exact Fit in Structural Equation Models

Abstract

We examine the accuracy of p values obtained using the asymptotic mean and variance (MV) correction to the distribution of the sample standardized root mean squared residual (SRMR) proposed by Maydeu-Olivares to assess the exact fit of SEM models. In a simulation study, we found that under normality, the MV-corrected SRMR statistic provides reasonably accurate Type I errors even in small samples and for large models, clearly outperforming the current standard, that is, the likelihood ratio (LR) test. When data shows excess kurtosis, MV-corrected SRMR p values are only accurate in small models ( p = 10), or in medium-sized models ( p = 30) if no skewness is present and sample sizes are at least 500. Overall, when data are not normal, the MV-corrected LR test seems to outperform the MV-corrected SRMR. We elaborate on these findings by showing that the asymptotic approximation to the mean of the SRMR sampling distribution is quite accurate, while the asymptotic approximation to the standard deviation is not.

Assessing the Relationship between Market Orientation and Green Product Innovation: The Intervening Role of Green Self-Efficacy and Moderating Role of Resource Bricolage

“…The predictive power of the model should be larger than 0 [92]; Q2 values show moderate predictive significance as suggested by the study of (0.02 = minor, 0.15 = moderate, and 0.35 = enormous) [93]. The standardized root mean square residual (SRMR) value according to the threshold need to be less than 0.08 [94,95], which is consistent with the results. R2 (R square) explains the predictive power of the model [96] with the values of 0.75 = substantial, 0.5 = moderate, and 0.25 = weak, as suggested by [83].…”

Effects of Coronavirus-19 Induced Loneliness on Mental Health: Sleep Quality and Intolerance for Uncertainty as Mediators

“…Researchers should try to explain why the indices disagree. Studies suggest that in small samples ( N <500), the estimates of the sample fit indices, mainly CFI and TLI, are likely to be biased and yield a far worse fit than their population values ( 33 , 34 ). Our sample size is <500, belonging to small samples, which may be the main reason for the inconsistency of evaluation indexes.…”

The Centrality of Events, Religion, Spirituality, and Subjective Well-Being in Latin American Jewish Immigrants in Israel

“…Finally, the relations between Centrality of Events, Religion, Spirituality, and SWB in Latin American Jewish Immigrants in Israel were tested using structural equation modeling, evaluated from the CFA model fitting solution by the Standardized Root Mean Squared Residual (SRMR), as it is suggested for continuum variables (Shi et al, 2018;Pavlov et al, 2020). The results indicated a good model fit ( Table 5).…”