Isle of Skye, June 2019
Research: Questions concerning causal relationships are at the core of science; understanding causality is also increasingly important in data applications in technology, business and policy. At the same time, unparalleled recent growth in the scale of data collection presents correspondingly exceptional opportunities to learn from this data. However, making credible inferences about causal relationships remains difficult.
The enormous amounts of observational data available presents great power to understand our world. However, with great power comes great responsibility. We must take care to address explicitly and rigorously the ways in which observational data complicates scientific investigation. A difficulty with all data (observational or otherwise) is that not all possible units are observed. The sample of data is selected in some way. Scrupulously considering and incorporating the mechanism through which a sample is selected is fundamental to the responsible practice of causal inference.
My research aims to elucidate what is required to make reliable causal inferences in the sample. That is, I focus on the problem of sample selection as pertains to understanding causal relationships in the sample at hand. I have developed graphical tools that aid researchers and analysts in determining why and how sample selection can bias inferences. These tools also demonstrate if and how such bias can be eliminated. I am in the process of incorporating these graphical tools into common observational and quasi-experimental research designs such as instrumental variables, difference-in-differences, regression discontinuity, and others. I am also developing sensitivity analyses focused on how sample selection can violate important design assumptions and change the inferences we are able to make.
Background: Before UCLA, I worked at Charles River Associates for 6 years conducting econometric investigations related to mergers, acquisitions, market dynamics, and antitrust litigation. It was here that my interest in the intersection of data, causality, and credible inference caught fire. Much of my work focused in the healthcare space, but spanned a variety of industries. I have expertise working with large databases (up to a few terabytes) to draw insights for clients and understand markets using a variety of data science, statistical, and econometric tools and methods.
I did my undergrad at Boston College, where I studied, separately, pure mathematics and economics. I did econometric research with Bob Murphy related to whether inflation expectations respond rationally to food and energy price movements. This work was presented at the 2015 AEA Meetings in Boston and published in the Eastern Economic Journal.
I grew up in Minnesota, lived in Boston for eight years, spent two years in Berkeley and Oakland, and moved to Los Angeles in the summer of 2019.
Don’t hesitate to reach out!
Elkhart Lake, WI, July 2019