Sampling Weights in Latent Variable Modeling

By T. Asparouhov. 2005

628 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/0f02133c1836fc921a61456c271ca9c7e4dec93d

How researchers see this paper

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

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

Complementary Variable- and Person-Centered Approaches to the Dimensionality of Psychometric Constructs: Application to Psychological Wellbeing at Work (2016, methodology): “2 (Muthén and Muthén 2014) robust weight least square estimator using diagonal weight matrices (WLSMV) and taking into account teachers’ nesting within schools with the Mplus design-based correction of standard errors (Asparouhov 2005).”
Why Tenth Graders Fail to Finish High School: A Dropout Typology Latent Class Analysis (2012, methodology): “…not a simple random sample, but rather used a complex probabilistic sampling strategy to allow for generalization to all 3 million students who were in grade 10 in the United States in 2002 (Ingles et al., 2007; Strayhorn, 2009), applying sample weights to the LCA is recommended (Asparouhov, 2005).”
Maximizing Gender Equality by Minimizing Course Choice Options? Effects of Obligatory Coursework in Math on Gender Differences in STEM (2017, methodology): “…nested within classes), standard errors were adjusted by applying a design-based correction as implemented in Mplus (Muthén & Muthén, 2012), which automatically takes the multilevel structure into account and makes use of a sandwich estimator (see, e.g., Asparouhov, 2005; Muthén & Satorra, 1995).”
The Model-Size Effect on Traditional and Modified Tests of Covariance Structures (2007, background): “In a recent Monte Carlo investigation, Asparouhov (2005) found the adjusted chi-square statistic to have excellent Type I error rates compared to T ML and T SC .”
Evaluating Model Fit With Ordered Categorical Data Within a Measurement Invariance Framework: A Comparison of Estimators (2014, methodology): “For more detail on why the metric and scalar should be constrained in tandem see Muthén and Asparouhov (2002). This procedure was used whether data were assumed to be ordered categorical (estimated λ and τ with WLSMV) or continuous (estimated λ and ν with ML and MLR).”
Going soft: on how Subjective Variables Explain Modal Choices for Leisure Travel (2011, methodology): “The parameters θ of the structural model are estimed by minimizing the objective function (Asparouhov, 2005):”
lavaan.survey: An R Package for Complex Survey Analysis of Structural Equation Models (2014, methodology): “…literature: adjustment of the weights or sample size to an eﬀective sample size (Stapleton 2002), pseudo-maximum likelihood (Muth´en and Satorra 1995; Asparouhov 2005, 2006), and weighted least squares estimation (Skinner et al. 1989, p. 86); see Stapleton (2006) for an overview of these…”
Teachers’ occupational attributes and their psychological wellbeing, job satisfaction, occupational self-concept and quitting intentions (2018, methodology): “The MLR estimator provides parameter estimates, standard errors, and goodness-of-fit results that are robust to the non-normality of the Likert scales underlying responses to the EdMAP items, and to the clustering of teachers within schools when used (as in the current study) jointly with Mplus COMP”
Relationships among perceived motivational climate, motivational regulations, enjoyment, and PA participation among Finnish physical education students (2017, methodology): “A COMPLEX option was used to correct a possible nonindependence of the observations based on students being nested within their PE classes (Asparouhov, 2005).”
PROC LCA: A SAS Procedure for Latent Class Analysis (2007, background): “Fitting latent class models in samples that are not simple random samples is a topic of current research (see, eg, Asparouhov, 2005 ).”
Initial Construction of a Maladaptive Personality Trait Model and Inventory for DSM-5 (2011, methodology): “Sampling weights were applied in all analyses (Asparouhov, 2005) to adjust the current sample demographics to be representative of the US population (and, at Rounds 1 and 2, taking into account our study-specific inclusion criterion of having seen a psychiatrist or psychologist).”
A practical guide to the analysis of non-response and attrition in longitudinal research using a real data example (2018, background): “Examples of such strategies include selection models, range restriction corrections, data weighting, maximum-likelihood, multiple imputation, pattern mixture models, and random coefficient models (e.g., Asparouhov, 2005; Enders, 2011; Sackett & Yang, 2000; Schafer & Graham, 2002).”
An Assessment of Practical Solutions for Structural Equation Modeling with Complex Sample Data (2006, background): “Using conventional SEM, Kaplan and Ferguson (1999) and Asparouhov (2005) demonstrate the parameter estimate bias that can result when unequal selection rates are ignored.”
Creating Birds of Similar Feathers: Leveraging Similarity to Improve Teacher-Student Relationships and Academic Achievement. (2015, methodology): “WLSMV-complex, which uses a variance correction procedure to account for clustered data, provides corrected SEs, confidence intervals (CIs), and coverage (Asparouhov, 2005).”
General Multi-Level Modeling with Sampling Weights (2006, methodology): “Simulation studies based on this approach are conducted in Asparouhov (2005). The situation is completely different when weights are present at level 1 because the unequal probability of selection is applied to dependent units and thus the assumptions of the single-level methodology are violated. Th”
Evaluating Measurement Invariance of TALIS 2013 Complex Scales: Comparison between Continuous and Categorical Multiple-Group Confirmatory Factor Analyses (2014, methodology): “To accommodate the sampling weights in both categorical and continuous model and to avoid biased estimates of the standard error, pseudo-maximum likelihood (PML) is implemented in Mplus for both MGCFA modellings with MLR and WLSMV estimators (Asparouhov, 2005).”