Auxiliary Variables in Mixture Modeling: Three-Step Approaches Using Mplus

By T. Asparouhov, B. Muthén. 2014

3,301 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/1d6fce2254f0cd6aed309696ae45b2b8ebd500d0

How researchers see this paper

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

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Stability, change, and implications of students’ motivation profiles: A latent transition analysis (2017, methodology): “Following Morin and Litalien’s (2017) recommendations, all LTA were estimated using the manual auxiliary 3-step approach described by Asparouhov and Muthén (2014).”
Career adaptability profiles and their relationship to adaptivity and adapting (2015, methodology): “Analyses were performed with the BCH procedure in MPlus 7.3.”
A person‐centered approach to commitment research: Theory, research, and methodology (2016, background): “Whenever this is the case, associations between inactive outcomes and the profiles can also be easily tested using a variety of auxiliary approaches (e.g., Asparouhov & Muthén, 2014; Lanza, Tan, & Bray, 2013; Vermunt, 2010).”
A Comparison of Three-Step Approaches for Auxiliary Variables in Latent Class and Latent Profile Analysis (2017, methodology): “Consistent with Vermunt (2010), Bakk, Tekle, and Vermunt (2013), and Asparouhov and Muthén (2014), Vermunt’s method has been shown to perform better than the PC method for analyzing LCA models with covariates as the latent class predictor under a variety of conditions.”
Performance of the entropy as an index of classification accuracy in latent profile analysis: A Monte Carlo simulation study (2017, neutral): “…也是研究的主要兴趣。例如, 在临床诊断上, 根据 LPA/LCA 的结果将不同患者归入不同的临床分组, 分类的精确性将会影响诊断的有效性。在 LPA/LCA 模型中, 通常使用 Entropy 作为分类精确性的指标, 取值范围在 0~1 之间, 越接近 1 表明分类越精确。其计算公式如下： ( log ) 1 log ik iki k k p p E n K (3) 其中, Pik 为估计第 i 个个体属于第 k 个类别的后验概率, n 为样本量。Pik 可通过如下贝叶斯后验概率获得： ( ) ( | )( | ) ( ) i i i i i i p…”
MplusAutomation: An R Package for Facilitating Large-Scale Latent Variable Analyses in Mplus (2018, methodology): “The creators of M plus regularly make substantive contributions to the SEM literature (e.g., Asparouhov & Muthén, 2014; Muthén & Asparouhov, 2012) and consistently implement these new methods in M plus .”
Impact of Misspecifications of the Latent Variance–Covariance and Residual Matrices on the Class Enumeration Accuracy of Growth Mixture Models (2016, result): “Similar values are frequently seen in simulation studies (e.g., Asparouhov & Muthen, 2014; Bakk, Oberski, & Vermunt, 2014; Vermunt, 2010).”
Multiple-Group Analysis of Similarity in Latent Profile Solutions (2016, methodology): “…tests of predictive and explanatory similarity require the direct incorporation of covariates into the model and have not yet been implemented using covariates specified as inactive (i.e., using auxiliary functions, e.g., Asparouhov & Muthén, 2014; Lanza, Tan, & Bray, 2013; Vermunt, 2010).”
Informative tools for characterizing individual differences in learning: Latent class, latent profile, and latent transition analysis (2017, background): “For example, it can be impractical if multiple covariates are of interest, as models would need to be re-estimated to test the significance of each covariate (Asparouhov & Muthén, 2014).”
Robustness of Stepwise Latent Class Modeling With Continuous Distal Outcomes (2016, methodology): “However, as suggested by Asparouhov and Muthén (2014), a much simpler solution is to use the empirical distribution of Z, which involves replacing the integral in Equation 6 by a sum over the N sample units and replacing f (Z) in Equation 7 by 1N .”