- Bayesian Anal.
- Advance publication (2020), 27 pages.
Using Bayesian Latent Gaussian Graphical Models to Infer Symptom Associations in Verbal Autopsies
Learning dependence relationships among variables of mixed types provides insights in a variety of scientific settings and is a well-studied problem in statistics. Existing methods, however, typically rely on copious, high quality data to accurately learn associations. In this paper, we develop a method for scientific settings where learning dependence structure is essential, but data are sparse and have a high fraction of missing values. Specifically, our work is motivated by survey-based cause of death assessments known as verbal autopsies (VAs). We propose a Bayesian approach to characterize dependence relationships using a latent Gaussian graphical model that incorporates informative priors on the marginal distributions of the variables. We demonstrate such information can improve estimation of the dependence structure, especially in settings with little training data. We show that our method can be integrated into existing probabilistic cause-of-death assignment algorithms and improves model performance while recovering dependence patterns between symptoms that can inform efficient questionnaire design in future data collection.
Bayesian Anal., Advance publication (2020), 27 pages.
First available in Project Euclid: 24 September 2019
Permanent link to this document
Digital Object Identifier
Li, Zehang Richard; McComick, Tyler H.; Clark, Samuel J. Using Bayesian Latent Gaussian Graphical Models to Infer Symptom Associations in Verbal Autopsies. Bayesian Anal., advance publication, 24 September 2019. doi:10.1214/19-BA1172. https://projecteuclid.org/euclid.ba/1569290444
- Supplementary Material to “Using Bayesian Latent Gaussian Graphical Models to Infer Symptom Associations in Verbal Autopsies”. PDF document of supplementary material. The replication R and Java codes to implement the proposed method can be found in the repository at https://github.com/richardli/LGGM.