Distributional assumptions of growth mixture models: implications for overextraction of latent trajectory classes.

By Daniel J. Bauer, P. Curran. Psychological methods, 2003

983 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Genetics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/64d15cdfe4cc24d3995f33943573808228b3a4c9

How researchers see this paper

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

In Computer Networks and Communications

In Genetics

In Statistics and Probability

Citations in the corpus

Local solutions in the estimation of growth mixture models. (2006, background): “In addition to these implications for problems of estimation, violating the distributional assumptions of the model can create problems for model selection and interpretation, for instance, leading to the estimation of spurious classes (Bauer & Curran, 2003).”
Robustness of Stepwise Latent Class Modeling With Continuous Distal Outcomes (2016, background): “Such a misspecification can even lead to overextraction of the classes (Bauer & Curran, 2003).”
A person‐centered approach to commitment research: Theory, research, and methodology (2016, background): “When this occurs, it suggests that the model may have been overparameterized (e.g., too many profiles and too many parameters freely estimated across profiles: e.g., Bauer & Curran, 2003) and thus that a more parsimonious model should be selected.”
Fuzzy Profiles (2018, background): “In the event that allowing the residuals to vary creates issues with model convergence, scholars can also model residuals as fixed (Bauer & Curran, 2003; Chen, Bollen, Paxton, Curran, & Kirby, 2001; Morin, Meyer, Creusier, & Biétry, 2016).”
Estimating the Association between Latent Class Membership and External Variables Using Bias-adjusted Three-step Approaches (2013, background): “A related problem with the one-step approach is that the inclusion of covariates or distal outcomes can distort the class solution because additional assumptions are made that may be violated (Bauer and Curran 2003; Tofighi and Enders 2008; Huang et al. 2010; Petras and Masyn 2010).”
General Growth Mixture Analysis with Antecedents and Consequences of Change (2010, neutral): “In concert with the growing popularity of these data-driven, group-based methods for studying developmental and life-course behavior trajectories, have come active and spirited ontological discussions about the nature of the emergent trajectory groups resulting from the analyses ( Bauer and Curran 2”
How Well Does Growth Mixture Modeling Identify Heterogeneous Growth Trajectories? A Simulation Study Examining GMM's Performance Characteristics (2012, methodology): “Second, Rindskopf noted that Bauer and Curran (2003a) did not examine the possibility that their homogeneous nonnormally distributed data were actually intrinsically normally distributed, or that a linear transformation might result in normally distributed data that might have been accurately…”
Overextraction of latent trajectory classes: Much ado about nothing? Reply to Rindskopf (2003), Muthén (2003), and Cudeck and Henly (2003) (2003, background): “Although intriguing, we can-Figure 1. Estimated densities for the population distributions of the first and last time points (y0 and y4 )o f the growth model considered in Bauer and Curran (2003) for a single replicate from the Skew 1.5 Kurtosis 6 condition.”
Methods and Measures: Growth mixture modeling: A method for identifying differences in longitudinal change among unobserved groups (2009, background): “There are real dangers of finding and identifying false groups (see Bauer & Curran, 2003a, 2004, and associated commentaries).”
A Multilevel Mixture IRT Model With an Application to DIF (2010, background): “The substantive usefulness of the MMixIRTM is based on the assumption that the resulting latent classes represent discrete subpopulations and are not just statistical artifacts of nonnormality that may incidentally exist in the data (Bauer & Curran, 2003).”
Detecting Mixtures From Structural Model Differences Using Latent Variable Mixture Modeling: A Comparison of Relative Model Fit Statistics (2007, background): “…to explore conditions in which LVMM would mistakenly indicate multiple populations when the data were sampled from a single, nonnormal population (Bauer & Curran, 2003), our simulation focuses on identifying conditions in which the LVMM estimation technique would be more likely to mistakenly…”
General Growth Mixture Analysis of Adolescents' Developmental Trajectories of Anxiety: The Impact of Untested Invariance Assumptions on Substantive Interpretations (2011, background): “One important set of criteria used to guide this decision is related to the substantive meaning and theoretical conformity of the extracted classes (Bauer & Curran, 2003; Marsh, Lüdtke, et al., 2009; B. O. Muthén, 2003), as well as to the statistical adequacy of the solution (Bauer & Curran, 2003).”
Dual commitment to organization and supervisor: A person-centered approach (2015, background): “Statistical and substantive checking in growth mixture modeling: Comment on Bauer and Curran (2003).”
A Skew-Normal Mixture Regression Model (2014, neutral): “Liu and Lin 141 Even a mild violation of within-class normality in these MRMs may result in the overextraction of unobserved groups in an attempt to fit the data (Bauer & Curran, 2003, 2004; Maclean, Morton, Elston, & Yee, 1976; McLachlan & Peel, 2000).”
Investigating population heterogeneity with factor mixture models. (2005, background): “Determining the number of classes is the subject of a stillgrowing body of research and has led to interesting discussions ( Bauer & Curran, 2003a; Bauer & Curran, 2003b; Cudeck & Henly, 2003; B. O. Muthe ´n, 2003; Rindskopf, 2003).”