Environmental Mixtures

Traditionally, environmental health studies have focused on assessing risks related to a single pollutant at a time. This, however, does not reflect reality, since we are constantly exposed to multiple pollutants at once. Recently, there has been an increased interest in methods that allow researchers to assess exposures to many pollutants at a time. These methods are able to accommodate the high dimension of the exposure matrix, as well as the usually high correlation across exposures of interest.

This two-day intensive workshop will provide a rigorous introduction to multiple different techniques to analyze exposure to mixtures in environmental health. Led by a team of world experts in environmental health, epidemiology and statistics, many of whom have developed their own methods to analyze exposure to mixtures, the workshop will integrate seminar lectures with hands-on computer lab sessions to put concepts into practice. Emphasis will be given to supervised and unsupervised methods. Since the choice of method depends on the research question at hand, the workshop will conclude with a panel discussion on when each method presented is appropriate for use and for which research questions.

By the end of the workshop, participants will be familiar with the following topics:

• Principal Component Analysis (PCA)
• Factor Analysis (FA)
• Clustering
• Variable Selection (Lasso, elastic net)
• Bayesian Kernel (BKMR)
• Weighted Quantile Sum Regression (WQS)
• Emerging mixtures topics and novel extensions
• Tree-based methods