Latent class models for classification

Abstract

This paper gives an overview of recent developments in the use of latent class or finite mixture models for classification purposes and presents several extensions of the proposed models. Two basic types of LC models and their most important special cases are presented and illustrated with an empirical example.

Psychological Disorders After Stroke Are an Important Influence on Functional Outcomes

“…As a solution, we chose to establish latent classes, that is, clusters of patients representing patterns of psychological symptoms during rehabilitation. [11][12][13] We undertook the final regression on these latent classes rather than the repeated measures. This approach had the added benefit of yielding latent classes that described trajectories of psychological symptoms in patients with stroke so that the clusters themselves were useful secondary outcomes of the analysis.…”

Comparing methods of classifying life courses: sequence analysis and latent class analysis

“…This mixture model (e.g. McLachlan & Peel, 2000) is closely related to supervised Naive Bayes classifiers (Hand & Yu, 2001;Vermunt & Magidson, 2003). Despite the highly implausible assumption of local independence (Rennie, Shih & Karger, 2003), such models often perform quite well for classification tasks because dependencies often are equal across classes or cancel out (Zhang, 2005).…”

Configurations of knowledge transfer relations: An empirically based taxonomy and its determinants

“…We performed the latent class cluster analysis by applying LatentGold 3.0 software (Vermunt and Magidson, 2003). The analysis begins by fitting a baseline model for one latent class only.…”