TY - JOUR
T1 - Latent Class Models for Stage-Sequential Dynamic Latent Variables
AU - Collins, Linda M.
AU - Wugalter, Stuart E.
N1 - Funding Information:
Requests for reprints may be sent to Linda M. Collins, J. P. Guilford Laboratory of Quantitative Psychology, University of Southern California, Los Angeles, CA 90089-1 061. This research was supported by National Institute on Drug Abuse grant DA411 I. The authors are grateful to the following: N. K. (Jacob) Chung for contributions to this research; Frank van de Pol, John W. Graham, and several anonymous reviewers for helpful comments; and Matthew D. Graham for preparing the figures.
PY - 1992/1/1
Y1 - 1992/1/1
N2 - Stage-sequential dynamic latent variables are of interest in many longitudinal studies. Measurement theory for these latent variables, called Latent Transition Analysis (LTA), can be found in recent generalizations of latent class theory. LTA expands the latent Markov model to allow applications to more complex latent variables and the use of multiple indicators. Because complex latent class models result in sparse contingency tables, that may lead to poor parameter estimation, a simulation study was conducted in order to determine whether model parameters are recovered adequately by LTA, and whether additional indicators result in better measurement or in impossibly sparse tables. The results indicated that parameter recovery was satisfactory overall, although as expected the standard errors were large in some conditions with few subjects. The simulation also indicated that at least within the conditions examined here, the benefits of adding indicators outweigh the costs. Additional indicators improved standard errors, even in conditions producing extremely sparse tables. An example of LTA analysis of empirical data on math skill development is presented.
AB - Stage-sequential dynamic latent variables are of interest in many longitudinal studies. Measurement theory for these latent variables, called Latent Transition Analysis (LTA), can be found in recent generalizations of latent class theory. LTA expands the latent Markov model to allow applications to more complex latent variables and the use of multiple indicators. Because complex latent class models result in sparse contingency tables, that may lead to poor parameter estimation, a simulation study was conducted in order to determine whether model parameters are recovered adequately by LTA, and whether additional indicators result in better measurement or in impossibly sparse tables. The results indicated that parameter recovery was satisfactory overall, although as expected the standard errors were large in some conditions with few subjects. The simulation also indicated that at least within the conditions examined here, the benefits of adding indicators outweigh the costs. Additional indicators improved standard errors, even in conditions producing extremely sparse tables. An example of LTA analysis of empirical data on math skill development is presented.
UR - http://www.scopus.com/inward/record.url?scp=0001398981&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0001398981&partnerID=8YFLogxK
U2 - 10.1207/s15327906mbr2701_8
DO - 10.1207/s15327906mbr2701_8
M3 - Article
AN - SCOPUS:0001398981
SN - 0027-3171
VL - 27
SP - 131
EP - 157
JO - Multivariate Behavioral Research
JF - Multivariate Behavioral Research
IS - 1
ER -