I am an assistant teaching professor in Carnegie Mellon's Department of Statistics & Data Science.

My main research interests are experimental design and causal inference. Most of my work tackles theoretical/methodological/applied questions that can be posed as, "Does a treatment cause a change in outcomes?" Topics I'm especially interested in are (in alphabetical order): covariate balance, doubly robust estimation, matching, randomization tests and other nonparametric methods, regression discontinuity designs, rerandomization and other balance-constrained designs, treatment effect heterogeneity, and weighting methods. In terms of applications, I primarily work in education, epidemiology, mental health, psychology, and text analysis. See my Google Scholar Page.

My main teaching interests are (1) teaching the above topics to undergraduates and non-statistics audiences, and (2) statistical communications (writing, presentations, and visualizations). Several of my courses culminate into students creating public-facing statistical objects that I call a part of their "data science portfolio" (for examples, see here). If you're an undergraduate CMU statistics major interested in research, I recommend taking one of our capstone courses (36-490, 36-493, 36-497), which I and other faculty are involved in most semesters. Taking 36-490 was my token "how I fell in love with statistics" story when I was an undergrad at CMU.

I received a PhD in Statistics from Harvard University in 2019. My dissertation committee was Tirthankar Dasgupta, Luke Miratrix, and José Zubizarreta. Before that, I received a B.S. in Economics and Statistics and a B.A. in Professional Writing from Carnegie Mellon University in 2014. I was born and raised in Louisville, Kentucky, where I received an excellent education from Jefferson County Public Schools. In my spare time I run, read non-statistics books, and play guitar and chess.

Email: zach [at] stat.cmu.edu