Distributionally-Weighted Least Squares in Growth Curve Modeling
Bibliographic Data
| ID | 21641963 |
|---|---|
| Authors | Han Du (0000-0001-7538-7789, University of California, corresponding author), Peter M Bentler (0000-0002-9440-721X, University of California), Yves Rosseel (0000-0002-4129-4477, Ghent University) |
| Year | 2022 |
| Volume | 29 |
| Issue | 1 |
| Pages | 1-22 |
| Publication date | 2022-01-02 |
| Peer Reviewed | Yes |
| Open Access | No |
| Type | ARTICLE |
| Venue | Structural Equation Modeling: A Multidisciplinary Journal (JOURNAL) |
| Journal identifiers | ISSN: 1070-5511 • E-ISSN: 1532-8007 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/10705511.2021.1931870 |
| OpenAlex | W3192997723 |
| Language | EN |
| Citations received | 4 |
| References cited | 30 |
Growth curve modeling is commonly used in psychological, educational, and social science research. The mainstream estimators for growth curve modeling are based on normal theory, but real data are unlikely to be exactly normally distributed. To improve estimation and inference with non-normal data, various estimators have been proposed. Among these estimators, the asymptotically distribution free (ADF) estimator does not need to rely on any distribution assumption but it is not efficient with small and modest sample sizes. We propose a distributionally weighted least squares DLS estimator in the growth curve modeling framework. DLS combines normal theory based and ADF based generalized least squares estimation to balance the information from the data and the normality assumption. Computer simulation results suggest that model-implied covariance-based DLS (DLSM) generally provides more accurate and efficient estimates than the examined alternative methods regardless of the distribution. In addition, the relative biases of standard error estimates and the Type I error rates of the Satorra–Bentler test statistic (TSB) in DLSM were competitive with the classical methods including maximum likelihood and generalized least squares estimation. We illustrate how to implement DLSM and select the optimal tuning parameter by a bootstrap procedure in a real data example
Asymptotic distribution · Covariance · Estimator · Generalized least squares · Least-squares function approximation · Mathematical optimization · Non-linear least squares · Normal distribution · Normality · Ordinary least squares · Statistical hypothesis testing · Statistical inference · Statistics · Test statistic · Mathematics · Psychometric Methodologies and Testing · Spatial and Panel Data Analysis · Statistical Methods and Bayesian Inference · Applied Mathematics
Applied Longitudinal Data Analysis
Statistical Power Analysis for the Behavioral Sciences
Robustness?
Some Contributions to Maximum Likelihood Factor Analysis
Maximum Likelihood Estimation of Misspecified Models
A General Approach to Confirmatory Maximum Likelihood Factor Analysis
Asymptotically distribution‐free methods for the analysis of covariance structures
Measures of multivariate skewness and kurtosis with applications
A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity
Computational Options for Standard Errors and Test Statistics with Incomplete Normal and Nonnormal Data in SEM
Fitting latent growth models with small sample sizes and non-normal missing data
The relation between adolescent alcohol use and peer alcohol use
Testing Variance Components in Linear Mixed Modeling Using Permutation
The longitudinal course of marital quality and stability
Univariate and multivariate skewness and kurtosis for measuring nonnormality
Can test statistics in covariance structure analysis be trusted
Bootstrapping Goodness-of-Fit Measures in Structural Equation Models
| Unique citing works | 4 |
|---|---|
| Citations per year | 1 |
| Citation span | 2022 - 2024 (3) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 3 |