- This event has passed.
Dr. Elena Colicino: Cross-Cohort Mixture Analysis: A Data Integration Approach with Applications on Child Health Outcomes
Cross-Cohort Mixture Analysis: A Data Integration Approach with Applications on Child Health Outcomes
Key Takeaways:
- Integrating data across multiple studies can enhance the statistical power of analyses and help researchers better understand the association between a mixture of chemical exposures and health outcomes.
- It can be challenging to combine data from multiple studies, especially when there are variations in data collection practices.
- The Bayesian Weighted Quantile Sum statistical approach allows researchers to aggregate data from multiple ECHO Cohort study sites to calculate an overall mixture index that identifies the most harmful exposure(s) across sites.
- This statistical approach also provides researchers with site-specific associations between chemical mixtures and health outcomes.
Speaker:
Dr. Elena Colicino, PhD, MSc
Associate Professor at Icahn School of Medicine at Mount Sinai
Speaker Bio:
Elena is an Associate Professor at the Icahn School Medicine at Mount Sinai. She develops and applies novel statistical methods and machine learning approaches to environmental health data in order to assess the effect of multiple toxic chemicals on human health throughout life-course. Her research focuses on cardiometabolic and immunological impacts of multiple exposures, with a particular emphasis on vulnerable subgroups. In her spare time, she promotes gender diversity amongst the R-software community by promoting and participating in R-ladies events and meet-ups.
Link to Dr. Colicino Slides (Duke-affiliated access only)