5. Three Likelihood-Based Methods for Mean and Covariance Structure Analysis with Nonnormal Missing Data

By Ke-Hai Yuan, Peter M. Bentler. 2000

1,776 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/cf4ba0cbecb1cd155b109f31fcf1c0a37099b82f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

lavaan: An R Package for Structural Equation Modeling (2012, background): “Robust standard errors are also available, as is a scaled test statistic (Yuan and Bentler 2000) if the data are both incomplete and non-normal.”
A validity and reliability study of the coping self-efficacy scale. (2006, methodology): “Though preliminary examination of the items’ univariate distributions suggested the items possessed an approximately normal distribution, we opted to report a chi-squared test of model fit and parameter estimate standard errors that are robust to departures from normality (Yuan & Bentler, 2000).”
Effects of Missing Data Methods in Structural Equation Modeling With Nonnormal Longitudinal Data (2009, methodology): “The technical details can be founded in Yuan and Bentler (2000), Gold et al. (2003), and Savalei and Bentler (2005).”
High-Performance Work Systems and Job Control (2013, methodology): “The MLR estimator is asymptotically equivalent to the estimator proposed by Yuan and Bentler (2000).”
Missing Data in Educational Research: A Review of Reporting Practices and Suggestions for Improvement (2004, background): “Although the subsequent discussion may give the impression that Rubin’s mechanisms are mutually exclusive, note that all three may be present in a given data set (Yuan & Bentler, 2000).”
Toward Conceptual Clarity (2013, methodology): “…CFI (comparative fit index) and TLI (Tucker-Lewis fit index) indices are above .95, when RMSEA (root mean square error of approximation) and SRMR (standardized root mean residual) are below .05, and when the chi-square value has a nonsignificant p-value (Hu & Bentler, 1999; Yuan & Bentler, 2000).”
Using Exploratory Factor Analysis to Determine the Dimensionality of Discrete Responses (2015, methodology): “Robust maximum likelihood (MLR) methods take violations of multivariate normality into account by adjusting standard errors and ﬁt indices (Yuan & Bentler, 2000; Muthén & Muthén, 2010), but are not suited for discrete data either.”
Riskier Tests of the Validity of the Bifactor Model of Psychopathology (2019, methodology): “Continuous symptom dimension scores were analyzed using the MLR estimator (maximum likelihood with robust standard errors; Yuan & Bentler, 2000) to account for their nonnormality and using the “cluster” option to account for nonindependence of twins and siblings nesting within families.”
Is the ML Chi-Square Ever Robust to Nonnormality? A Cautionary Note With Missing Data (2008, methodology): “This was largely done by Yuan and Bentler (2000).”