TY - JOUR
T1 - A New Perspective on the Effects of Covariates in Mixture Models
AU - Stegmann, Gabriela
AU - Grimm, Kevin
N1 - Funding Information:
This work was supported by National Science Foundation Grant REAL-1252463 awarded to the University of Virginia, David Grissmer (Principal Investigator), and Christopher Hulleman (Co-Principal Investigator).
Publisher Copyright:
Copyright © Taylor & Francis Group, LLC.
PY - 2018/3/4
Y1 - 2018/3/4
N2 - In this simulation study, we explored the effect of introducing covariates to a growth mixture model when covariates were also generated by a mixture model. We varied the association between the latent classes underlying the growth trajectories and the covariates, the degree of separation between the latent classes underlying the covariates, the number of covariates included, and amount of missing data in the growth data. We found that adding covariates to the growth mixture model generally hurt class recovery except where the latent classes underlying the growth trajectories and the covariates were the same or very strongly associated, and there was a large degree of separation between the classes underlying the covariates. We found that when covariates were introduced, entropy might no longer be an accurate indicator of the distinctiveness of the growth trajectory classes.
AB - In this simulation study, we explored the effect of introducing covariates to a growth mixture model when covariates were also generated by a mixture model. We varied the association between the latent classes underlying the growth trajectories and the covariates, the degree of separation between the latent classes underlying the covariates, the number of covariates included, and amount of missing data in the growth data. We found that adding covariates to the growth mixture model generally hurt class recovery except where the latent classes underlying the growth trajectories and the covariates were the same or very strongly associated, and there was a large degree of separation between the classes underlying the covariates. We found that when covariates were introduced, entropy might no longer be an accurate indicator of the distinctiveness of the growth trajectory classes.
KW - covariates
KW - entropy
KW - finite mixture models
KW - growth mixture model
UR - http://www.scopus.com/inward/record.url?scp=85019253327&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85019253327&partnerID=8YFLogxK
U2 - 10.1080/10705511.2017.1318070
DO - 10.1080/10705511.2017.1318070
M3 - Article
AN - SCOPUS:85019253327
SN - 1070-5511
VL - 25
SP - 167
EP - 178
JO - Structural Equation Modeling
JF - Structural Equation Modeling
IS - 2
ER -