Join us to discuss how the latest statistics and data science methods can help address issues ranging from pandemics to human trafficking.
As policymakers and community leaders have worked to respond to the Covid-19 pandemic, it has become increasingly clear that statistics and data science can play a critical role in protecting public health and determining the best path forward. Moving from theory to practice presents challenges for working with a patchwork of data from many different sources across public and private sectors.
Join the National Academies for a symposium on June 10, 2021 from 1:00-5:30pm ET (6:00 PM – 10:30 PM BST) to explore the latest statistics and data science methods and how they can be applied to real-world situations. Speakers will discuss how their work in modeling, inference, predictive analysis, and machine learning has been applied to track the spread of Covid-19, drug use, air pollution, and human trafficking. Panelists will explore the strengths and weaknesses of available surveillance data and how to integrate and draw insight from multiple imperfect data sources.
Sessions and Speakers
Session 1: Data Collection, Surveillance, and Modeling
- Moderator: Amy Herring (Duke University)
- Data Fusion of Observations and Computer Model Output for Air Pollution Exposure Assessment, Veronica Berrocal (University of California Irvine)
- Effects of the Pandemic on Surveillance Surveys, Stephanie Eckman (RTI International)
- The Past, Present, and Future of Infectious Disease Forecasting, Nick Reich (University of Massachusetts Amherst)
- Delphi's COVIDcast Project: Lessons from building a digital ecosystem for tracking and forecasting the pandemic, Ryan Tibshirani (Carnegie Mellon University)
Session 2: Data Integration
- Moderator: Elizabeth Stuart (Johns Hopkins University)
- What's in a Model? Integrating Mechanistic and Statistical Models in HIV Epidemiology, Joe Hogan (Brown University)
- The Prevalence of Modern Slavery and Human Trafficking: Three approaches which may or may not work, what they tell us, and how they have made a difference, Bernard Silverman (University of Nottingham)
- Fusion Learning in Finance and Health Research: A statistical learning method for making targeted inference using integrated data information, Minge Xie (Rutgers University)
- Handling Selection Bias and Outcome Misclassification in Electronic Health Records: Reports from the Michigan Genomics Initiative, Bhramar Mukherjee (University of Michigan)
Find out more and register online.