featuring

Betsy Ogburn
Associate Professor of Biostatistics
Johns Hopkins Bloomberg School of Public Health

On February 9, 2021, Betsy Ogburn, Associate Professor of Biostatistics at Johns Hopkins Bloomberg School of Public Health, presented her talk, “Social Network Dependence and the Replication Crisis,” at the Women in Data Science (WiDS) @ Penn Conference.

Researchers across the social sciences are increasingly interested in using social network data to study ways in which our social ties affect our behavior, beliefs, and health. But statistical methodology has not kept pace with substantive research, and often researchers have no better option than to use traditional statistical models–models that were not created with networks in mind–to answer their social network research questions. Betsy showed that failing to adequately account for network structure can result in spurious effect estimates and artificially small p-values, confidence intervals, etc. In fact, this can happen even when researchers are not explicitly interested in networks but they collect data from a single college campus, hospital, school, or community and inadvertently sample subjects connected by social ties.

Women in Data Science (WiDS) @ Penn is an independent virtual event presented by the University of Pennsylvania to coincide with the annual Global WiDS Conference held at Stanford University and an estimated 150+ organizations worldwide. All genders are invited to attend WiDS regional events, which features outstanding women doing outstanding work. This year’s theme for WiDS Philadelphia @ Penn was: This is What a Data Scientist Looks Like.