Explore new methods.Exchange ideas. Build connections.

The Let’s Talk Data Tutorial Series connects our public health community with data resources, practical tools, and the expertise to use them thoughtfully. Join us for the first tutorial of the semester, Getting Started with PopHIVE, to explore the platform with the team behind it, consider its strengths and limitations, and discover how it might inform your research questions.

When do specialized causal inference methods add value beyond standard approaches? Drawing from her unique perspective as both an epidemiologist and a biostatistician, Donna Spiegelman will consider the circumstances under which commonly invoked causal assumptions are necessary for causal inferences to be validly made from data, arguing that often they are not. She will show that valid learning can occur 1) under conditions much less restrictive than required by current widely used methods, 2) when real-world implementation of interventions varies, and 3) when interventions spill over to others not directly exposed, thereby obviating components of the SUTVA assumption.

She will present evidence for her argument that measurement error is the major source of bias in observational research, not confounding, whose bias is rather tightly bounded. Finally, she will discuss the eternal challenge in science: after exhaustive efforts to collect data to predict important outcomes, a substantial proportion of the variation in occurrences of these outcomes appears to be entirely random.

A discussion will follow, featuring formal remarks by Lee Kennedy-Shaffer and contributions from Bhramar Mukherjee and others to examine and debate the ideas raised in the lecture. Refreshments will be provided after the lecture, in addition to food for thought.

This session will introduce MarketScan, a large-scale healthcare claims database available to Yale researchers, and explore how it can be used to support health and clinical research. Participants will learn about the populations and data available in MarketScan, see examples of research applications, and gain a practical understanding of how to request and access the data at Yale.

Topics will include

• Overview of MarketScan and its applications in healthcare research
• Available populations, data types, and key variables
• Examples of research questions and studies using claims data
• How to request MarketScan access through YBIC DataMed
• Accessing and navigating Yale’s secure data environment
• Available resources and research support

About the speaker

Yujia Zhou is a Data Analyst at Yale University supporting biomedical and clinical research using electronic health records, healthcare claims, and other large-scale research databases. She holds an M.S. in Biomedical Informatics and an MBBS, bringing together clinical training and expertise in data science.

Her work includes cohort development, data harmonization, cloud computing, and research support through DataMed. She has experience working with MarketScan, Epic, OMOP, and other real-world healthcare data sources.