Confirmatory Factor Analysis of Ordinal Variables With Misspecified Models

By Fan Yang-Wallentin, Karl G. Jöreskog, Hao Luo. 2010

312 citations recorded by the source corpus.

Subfields: Food Science, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/50c8d292d35a2f23fee6bb22b397272649d05571

How researchers see this paper

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

In Food Science

In Statistics and Probability

Citations in the corpus

Why Ordinal Variables Can (Almost) Always Be Treated as Continuous Variables: Clarifying Assumptions of Robust Continuous and Ordinal Factor Analysis Estimation Methods (2020, methodology): “Alternatively, ordinal variables can be modeled with ordinal marginal distributions (Forero et al., 2009; Yang-Wallentin et al., 2010).”
A Comparison of Diagonal Weighted Least Squares Robust Estimation Techniques for Ordinal Data (2014, methodology): “…here were higher than observed in previous studies of robust estimation techniques, when correctly specified models were used (e.g., Flora & Curran, 2004; Lei, 2009; Yang-Wallentin et al., 2010) and more in line with results from nonrobust WLS procedures (e.g., DiStefano, 2002; Potthast, 1993).”
Comparison of Different Estimation Methods for Categorical and Ordinal Data in Confirmatory Factor Analysis (2015, background): “The literature has many studies that compared different estimation methods which have effects on results obtained (DiStefano, 2002; Forero et al, 2009; Hu, Bentler & Kano, 1992; Lei, 2009; Muthen & Kaplan, 1985; Rigdon & Ferguson, 1991; Yang-Wallentin et al., 2010).”
Examining Chi-Square Test Statistics Under Conditions of Large Model Size and Ordinal Data (2018, result): “…did not observe substantial differences between different estimators (e.g., Bandalos, 2014; Flora & Curran, 2004; Savalei & Rhemtulla, 2013; Yang-Wallentin et al., 2010); however, this may be due to the smaller sizes of the tested models in these studies, where typically less than 30…”
Confirmatory factor analysis with ordinal data: Comparing robust maximum likelihood and diagonally weighted least squares (2016, methodology): “In addition, it is worth noting that the simulation studies of Lei (2009), Oranje (2003), and Yang-Wallentin et al. (2010) used a polychoric correlation matrix, instead of a samplebased covariance matrix, in ML with robust corrections to standard errors and chi-square statistics.”
When can categorical variables be treated as continuous? A comparison of robust continuous and categorical SEM estimation methods under suboptimal conditions. (2012, methodology): “These have reported very little bias in estimated standard errors (Flora & Curran, 2004; Forero et al., 2009; Lei, 2009; Maydeu-Olivares, 2001; Nussbeck et al., 2006; Yang-Wallentin et al., 2010).”
Sample Size Requirements of the Robust Weighted Least Squares Estimator (2014, unknown): “It has been shown that model misspecifications tend to increase the bias associated with parameter estimates and standard errors obtained through various least squares estimators, thus increasing sample size requirements (Yang-Wallentin et al., 2010).”
Examination of the Weighted Root Mean Square Residual: Evidence for Trustworthiness? (2018, background): “Bandalos (2008) and other studies investigating fit with robust estimators (e.g., DiStefano & Morgan, 2014; Flora & Curran, 2004; Maydeu-Olivares et al.,; Savalei, 2012; Yang-Wallentin et al., 2010) investigated the impact of factor loadings in such situations.”
RMSEA, CFI, and TLI in structural equation modeling with ordered categorical data: The story they tell depends on the estimation methods (2018, methodology): “It is also important to note that robust corrections are recommended to adjust the chi-square statistic and standard error when ML is employed for polychoric correlation matrices (e.g., Yang-Wallentin et al., 2010).”
A Bayesian Approach to Multilevel Structural Equation Modeling With Continuous and Dichotomous Outcomes (2015, background): “It is important to note that only dichotomous items were considered in this investigation; convergence rates might be higher for items with a larger number of categories (see, e.g., Yang-Wallentin et al., 2010).”
Developing Multidimensional Likert Scales Using Item Factor Analysis (2016, result): “However, on this matter, two points must be highlighted: (i) first, that using classical FA with WLS estimation is never a viable option for ordinal data, given the results presented here using Pearson correlation matrices and considering its poor results on tetra and polychoric correlation matrices”