Ian Lundberg is a Ph.D. student in sociology and social policy at Princeton University. He specializes in statistical methods, social stratification, and demography. Ian is especially fascinated by two sets of assumptions required to answer social science questions: untestable identification assumptions and estimation assumptions that may be relaxed. The former include identification assumptions about treatment assignment, survey nonresponse, missingness, etc. These assumptions are the core of social science, require substantive theory, and are often opaque in published papers. The latter include estimation assumptions such as parametric regression models. Ian’s research aims to make transparent the identification assumptions which cannot be weakened and to relax parametric assumptions where possible with flexible models targeted toward a particular estimand. Using this methodological framework, he aims to promote substantive research in social stratification that is transparent, accurate, and clear.
Sign up for periodic updates from Digital Impact. Opt out anytime.
Make an Impact
Digital Impact draws on insights into how digital systems work and how an independent and informed civil society can engage with them safely, ethically, and effectively. Make an impact here.