# Special Seminar in Computing and Mathematical Sciences

*,*Statistics

*,*Columbia University

*,*

Yixin Wang is a PhD student in the Statistics Department of Columbia University, advised by Professor David Blei. Her research interests lie in Bayesian statistics, machine learning, and causal inference. Prior to Columbia, she completed undergraduate studies in mathematics and computer science at the Hong Kong University of Science and Technology. Her research has received several awards, including the INFORMS data mining best paper award, student paper awards from American Statistical Association Biometrics Section and Bayesian Statistics Section, and the ICSA conference young researcher award.

Causal inference from observational data is a vital problem, but it

comes with strong assumptions. Most methods assume that we observe all

confounders, variables that affect both the causal variables and the

outcome variables. But whether we have observed all confounders is a

famously untestable assumption. We describe the deconfounder, a way to

do causal inference from observational data allowing for unobserved

confounding.

How does the deconfounder work? The deconfounder is designed for

problems of multiple causal inferences: scientific studies that

involve many causes whose effects are simultaneously of interest. The

deconfounder uses the correlation among causes as evidence for

unobserved confounders, combining unsupervised machine learning and

predictive model checking to perform causal inference. We study the

theoretical requirements for the deconfounder to provide unbiased

causal estimates, along with its limitations and tradeoffs. We

demonstrate the deconfounder on real-world data and simulation

studies.