Review of Advances in Latent Class Analysis
- 40 Downloads
For over four decades, latent class analysis (LCA) has received much attention and has been applied by both researchers and practitioners across a wide range of disciplines, including education, psychology, medicine, and the broader social and behavioral sciences. Researchers have traditionally viewed LCA as a tool to conduct categorical data analysis and to examine structural associations between categorical variables or as extensions of the log-linear model that control for measurement error, aimed toward obtaining classification or diagnostic groupings when the indicators (measuring items) and the latent variable are discrete (Heinen 1996). While these views address earlier notions of the approach, LCA has grown into a family of methods that provide insights for scientists and behavioral researchers to yield better classifications and study meaningful associations.
Different from item response theory (IRT) and latent trait models that generally view latent variables as continuous...
- Hancock, G. R., Harring, J. R., & Macready, G. B. (2019). Advances in latent class analysis: A festchrift in honor of C. Mitchell Dayton. Charlotte: Information Age Publishing Inc.Google Scholar
- Heinen, T. (1996). Latent class and discrete latent trait models: Similarities and differences. Thousand Oaks: Sage.Google Scholar