Emilija Perkovic

Emilija Perkovic serves as the Dorothy Gilford Early Career Endowed Professor in Mathematical Statistics within the Department of Statistics at the University of Washington. She joined the department in Autumn 2018 as an Acting Assistant Professor and advanced to a tenure-track Assistant Professor position in Autumn 2020, establishing herself as a core faculty member in statistical methodology.

Her academic foundation includes:

• B.Sc. in Mathematics from the University of Belgrade (2012)
• M.Sc. in Statistics from ETH Zürich (2014)
• Ph.D. in Statistics from ETH Zürich (2018) under Professor Marloes Maathuis

Perkovic's research pioneers causal inference methodologies through probabilistic graphical models, focusing on intuitive frameworks for causal identification and estimation from observational data. Her work bridges theoretical statistics with practical applications, particularly in covariate adjustment techniques and Markov equivalence class analysis. She actively integrates expert knowledge to refine causal models, making complex inference accessible for real-world data challenges where experimental intervention is impossible.

Her publication record reveals a concentrated evolution in causal graph theory, with recent preprints advancing adjustment criteria for diverse graph structures (MPDAGs, MAGs, ancestral graphs). Key trends include developing sound/complete identification rules, efficient estimation techniques under linearity, and minimal effect enumeration in equivalence classes—collectively enhancing robustness in observational causal analysis.

Her scientific recognition includes:

• Best Poster Award, Semantic Statistics (SEMSTAT), Statistical Network Science Workshop (2017)

While specific advising details and grant histories remain unreported in source materials, Perkovic's research trajectory indicates active mentorship through co-authored preprints with junior collaborators like Sara LaPlante and F. Richard Guo. Her Dorothy Gilford Endowed Professorship likely supports ongoing methodological innovation in causal statistics.

No laboratory or team structures are explicitly referenced in her professional profile, suggesting independent or collaborator-driven research within the Statistics Department framework.