Stepwise latent class models for explaining group-level putcomes using discrete individual-level predictors

Margot Bennink, M.A. Croon, J.K. Vermunt

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Explaining group-level outcomes from individual-level predictors requires aggregating the individual-level scores to the group level and correcting the group-level estimates for measurement errors in the aggregated scores. However, for discrete variables it is not clear how to perform the aggregation and correction. It is shown how stepwise latent class analysis can be used to do this. First, a latent class model is estimated in which the scores on a discrete individual-level predictor are used to construct group-level latent classes. Second, this latent class model is used to aggregate the individual-level predictor by assigning the groups to the latent classes. Third, a group-level analysis is performed in which the aggregated measures are related to the remaining group-level variables while correcting for the measurement error in the class assignments. This stepwise approach is introduced in a multilevel mediation model with a single individual-level mediator, and compared to existing methods in a simulation study. We also show how a mediation model with multiple group-level latent variables can be used with multiple individual-level mediators and this model is applied to explain team productivity (group level) as a function of job control (individual level), job satisfaction (individual level), and enriched job design (group level).
Keywords: latent class analysis, micro-macro analysis, multilevel analysis, discrete variables, stepwise modeling
Original languageEnglish
Pages (from-to)662-675
JournalMultivariate Behavioral Research
Volume50
Issue number6
DOIs
Publication statusPublished - 2015

Fingerprint

Latent Class Model
Job Satisfaction
Predictors
Efficiency
Latent Class Analysis
Latent Class
Mediation
Discrete Variables
Mediator
Measurement Error
Multilevel Analysis
Latent Variables
Productivity
Aggregation
Assignment
Simulation Study
Model

Cite this

@article{1002fa8dbb824d32ac55d428246b8dcb,
title = "Stepwise latent class models for explaining group-level putcomes using discrete individual-level predictors",
abstract = "Explaining group-level outcomes from individual-level predictors requires aggregating the individual-level scores to the group level and correcting the group-level estimates for measurement errors in the aggregated scores. However, for discrete variables it is not clear how to perform the aggregation and correction. It is shown how stepwise latent class analysis can be used to do this. First, a latent class model is estimated in which the scores on a discrete individual-level predictor are used to construct group-level latent classes. Second, this latent class model is used to aggregate the individual-level predictor by assigning the groups to the latent classes. Third, a group-level analysis is performed in which the aggregated measures are related to the remaining group-level variables while correcting for the measurement error in the class assignments. This stepwise approach is introduced in a multilevel mediation model with a single individual-level mediator, and compared to existing methods in a simulation study. We also show how a mediation model with multiple group-level latent variables can be used with multiple individual-level mediators and this model is applied to explain team productivity (group level) as a function of job control (individual level), job satisfaction (individual level), and enriched job design (group level).Keywords: latent class analysis, micro-macro analysis, multilevel analysis, discrete variables, stepwise modeling",
author = "Margot Bennink and M.A. Croon and J.K. Vermunt",
year = "2015",
doi = "10.1080/00273171.2015.1074879",
language = "English",
volume = "50",
pages = "662--675",
journal = "Multivariate Behavioral Research",
issn = "0027-3171",
publisher = "ROUTLEDGE JOURNALS, TAYLOR & FRANCIS LTD",
number = "6",

}

Stepwise latent class models for explaining group-level putcomes using discrete individual-level predictors. / Bennink, Margot; Croon, M.A.; Vermunt, J.K.

In: Multivariate Behavioral Research, Vol. 50, No. 6, 2015, p. 662-675.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Stepwise latent class models for explaining group-level putcomes using discrete individual-level predictors

AU - Bennink, Margot

AU - Croon, M.A.

AU - Vermunt, J.K.

PY - 2015

Y1 - 2015

N2 - Explaining group-level outcomes from individual-level predictors requires aggregating the individual-level scores to the group level and correcting the group-level estimates for measurement errors in the aggregated scores. However, for discrete variables it is not clear how to perform the aggregation and correction. It is shown how stepwise latent class analysis can be used to do this. First, a latent class model is estimated in which the scores on a discrete individual-level predictor are used to construct group-level latent classes. Second, this latent class model is used to aggregate the individual-level predictor by assigning the groups to the latent classes. Third, a group-level analysis is performed in which the aggregated measures are related to the remaining group-level variables while correcting for the measurement error in the class assignments. This stepwise approach is introduced in a multilevel mediation model with a single individual-level mediator, and compared to existing methods in a simulation study. We also show how a mediation model with multiple group-level latent variables can be used with multiple individual-level mediators and this model is applied to explain team productivity (group level) as a function of job control (individual level), job satisfaction (individual level), and enriched job design (group level).Keywords: latent class analysis, micro-macro analysis, multilevel analysis, discrete variables, stepwise modeling

AB - Explaining group-level outcomes from individual-level predictors requires aggregating the individual-level scores to the group level and correcting the group-level estimates for measurement errors in the aggregated scores. However, for discrete variables it is not clear how to perform the aggregation and correction. It is shown how stepwise latent class analysis can be used to do this. First, a latent class model is estimated in which the scores on a discrete individual-level predictor are used to construct group-level latent classes. Second, this latent class model is used to aggregate the individual-level predictor by assigning the groups to the latent classes. Third, a group-level analysis is performed in which the aggregated measures are related to the remaining group-level variables while correcting for the measurement error in the class assignments. This stepwise approach is introduced in a multilevel mediation model with a single individual-level mediator, and compared to existing methods in a simulation study. We also show how a mediation model with multiple group-level latent variables can be used with multiple individual-level mediators and this model is applied to explain team productivity (group level) as a function of job control (individual level), job satisfaction (individual level), and enriched job design (group level).Keywords: latent class analysis, micro-macro analysis, multilevel analysis, discrete variables, stepwise modeling

U2 - 10.1080/00273171.2015.1074879

DO - 10.1080/00273171.2015.1074879

M3 - Article

VL - 50

SP - 662

EP - 675

JO - Multivariate Behavioral Research

JF - Multivariate Behavioral Research

SN - 0027-3171

IS - 6

ER -