Abstract
Latent Class Models (LCMs) are used to cluster multivariate categorical data (e.g. group participants based on survey responses). Traditional LCMs assume a property called conditional independence. This assumption can be restrictive, leading to model misspecification and overparameterization. To combat this problem, we developed a novel Bayesian model called a Domain Latent Class Model (DLCM), which permits conditional dependence. We verify identifiability of DLCMs. We also demonstrate the effectiveness of DLCMs in both simulations and real-world applications. Compared to traditional LCMs, DLCMs are effective in applications with time series, overlapping items, and structural zeroes.
Acknowledgments
We would like to thank Theren Williams, Eric Wayman, and Dr. Kristen Lee for providing valuable feedback on writing style.
Citation
Jesse Bowers. Steve Culpepper. "Domain Latent Class Models." Bayesian Anal. Advance Publication 1 - 28, 2024. https://doi.org/10.1214/24-BA1433
Information