Air pollution, Fuel Usage and Health Outcomes in Madre de Dios, Peru: a Comparative Cross Sectional Study

Air pollution is a common problem. Particulate matter generated from air pollution has been tied to adverse health outcomes associated with cardiovascular disease. Biomass fuels are a specific contributor to increased particulate matter and arise as a result of indoor heating, cook stoves and indoor food preparation. This is a two part cross sectional study looking at communities in the Madre de Dios region. Survey data was collected from 9 communities along the Madre de Dios River. Individual level household PM2.5 was also collected as a means to generate average PM data stratified by fuel use. Data collection was affected by a number of outside factors, which resulted in a loss of data. Results from the cross-sectional study indicate that hypertension is not a significant source of morbidity. Obesity is prevalent and significantly associated with kitchen venting method indicating a potential relationship.

A Bayesian Dirichlet-Multinomial Test for Cross-Group Differences

Testing for differences within data sets is an important issue across various applications. Our work is primarily motivated by the analysis of microbiomial composition, which has been increasingly relevant and important with the rise of DNA sequencing. We first review classical frequentist tests that are commonly used in tackling such problems. We then propose a Bayesian Dirichlet-multinomial framework for modeling the metagenomic data and for testing underlying differences between the samples. A parametric Dirichlet-multinomial model uses an intuitive hierarchical structure that allows for flexibility in characterizing both the within-group variation and the cross-group difference and provides very interpretable parameters. A computational method for evaluating the marginal likelihoods under the null and alternative hypotheses is also given. Through simulations, we show that our Bayesian model performs competitively against frequentist counterparts. We illustrate the method through analyzing metagenomic applications using the Human Microbiome Project data.