Estimating Latent Structure Models with Categorical Variables: One-Step Versus Three-Step Estimators

By A. Bolck, Marcel A. Croon, J. Hagenaars. Political Analysis, 2004

1,238 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/4bccd2bff85c32e8199b64aaa5b9df8103aa7272

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

Prediction from Latent Classes: A Demonstration of Different Approaches to Include Distal Outcomes in Mixture Models (2019, methodology): “…using the data illustration in Appendix B (for Step 1) and Appendix C (for Step 3) and Latent Gold syntax in Appendix F. BCH method First introduced by Bolck et al. (2004) for categorical covariates, this method was referred to as the BCH method after the last names of the authors of the paper.”
Bias-Adjusted Three-Step Latent Markov Modeling With Covariates (2016, positive): “The correction methods proposed for three-step LC analysis (Bolck et al., 2004; Vermunt, 2010) start from the observation that in an unadjusted three-step estimation procedure, one analyzes the relationship between Wt and Zt, whereas the relationship of interest is the one between Xt and Zt.”
Robustness of Stepwise Latent Class Modeling With Continuous Distal Outcomes (2016, methodology): “Irrespective of the assignment method used, classification errors will be present unless the classification is perfect (Bolck et al., 2004).”
General Growth Mixture Analysis of Adolescents' Developmental Trajectories of Anxiety: The Impact of Untested Invariance Assumptions on Substantive Interpretations (2011, methodology): “Direct inclusion of the predictors in the model is known to result in a more precise estimation of their effects ( Bolck, Croon, & Hagenaars, 2004 ; Clark & Muthen, 2010 ) and in more accurate classifications ( Lubke & Muthen, 2007 ).”
poLCA: An R Package for Polytomous Variable Latent Class Analysis (2011, background): “However, as demonstrated by Bolck, Croon, and Hagenaars (2004), the three-step procedure produces biased coeﬃcient estimates.”
A Multifoci Person-Centered Perspective on Workplace Affective Commitment: A Latent Profile/Factor Mixture Analysis (2011, methodology): “This method has been shown to systematically reduce biases in the estimation of the model parameters, especially those describing the relationships between the predictors and the latent profiles (Bolck et al., 2004; Clark & Muthén, 2009).”
Technical Guide for Latent GOLD 5.1: Basic, Advanced, and Syntax 1 (2016, methodology): “Bolck et al. (2004) derived how the probability of interest, P (x|zi), is related to the probability that we can model using the class assignments, P (ai|zi); that is,”
Latent Class Modeling with Covariates: Two Improved Three-Step Approaches (2010, methodology): “Bolck, Croon, and Hagenaars (2004) demonstrated that such a three-step approach underestimates the associations between covariates and class membership.”
A Comparison of Three-Step Approaches for Auxiliary Variables in Latent Class and Latent Profile Analysis (2017, methodology): “Furthermore, the latent categorical variable might lose its meaning as the latent variable measured by the indicator variables (Bolck et al., 2004).”
Auxiliary Variables in Mixture Modeling: Three-Step Approaches Using Mplus (2014, methodology): “, for each observation, N is set to be the class c for which P (C = c|U) is the largest, where U represents the latent class indicators and C is the latent class variable.(2) The classification uncertainty rate for N is computed as follows pc1,c2 = P (C = c2|N = c1) = 1 Nc1 ∑ Ni=c1 P (Ci = c2|Ui)”
Estimating the Association between Latent Class Membership and External Variables Using Bias-adjusted Three-step Approaches (2013, methodology): “Bolck et al. (2004) proved that the estimates of the log-odds ratios characterizing the relationship between Z and W will always be smaller than those characterizing the relationship between Z and X and proposed a correction method that can be used with categorical external predictors (see Figure…”
All better than being disengaged: Student engagement patterns and their relations to academic self-concept and achievement (2020, methodology): “…self-concept, and achievement To answer the second and third research question, how academic self-concept predicts student engagement patterns, and how engagement patterns relate to subsequent achievement, a manual BCH three-step approach was conducted (Bakk et al. 2013; Bolck et al. 2004).”