Anna Bykhovskaya is an Assistant Professor at Duke University. She received a PhD in Economics from Yale University in 2019. Prior to Yale, Anna spent 5 years at the Moscow State University, where she earned BS and MS in Mathematics. She was mostly specializing in probability theory. Additionally, Anna holds an MA in Economics from the New Economic School.
In her research Anna aims to combine her knowledge of mathematics with real world problems, such as evolution of relationship across people or countries and long-run dependences among stock prices. In her latest project Anna creates new methods for analyzing high-dimensional non-stationary time series. Anna proposes a way (and derives the appropriate asymptotics) to examine a high-dimensional VAR for the presence of cointegration. The new method demonstrates superior theoretical properties, thus removing the need for various finite sample correction procedures previously used to address the known over-rejection problem of classical cointegration tests.