Luke Miratrix is currently an Assistant Professor at the Harvard Graduate School of Education. Prior to this, he spent three years as an assistant professor in the statistics department at Harvard. His primary interest, unsurprisingly, is to learn how to best use modern statistical methods in applied social science context.
In particular, he is currently interested in developing and applying minimal-assumption methods to applied problems. He is also interested in the issues that arise with high-dimensional data, in particular large text corpora. He has recently been working on projects in elections and voting systems, assessment of large-scale education field trials, media analysis, effectiveness of regulatory agencies such as OSHA, effectiveness of teacher development programs, and human-computer interactions.
He received his Doctorate in Statistics from University of California, Berkeley in Spring, 2012. His interest in Statistics came out of an interest in mathematics education which developed while being a high school teacher and tutor for 7 years. He also has a Masters in Computer Science from M.I.T., a Bachelors of Science in Computer Science from the California Institute of Technology, and a Bachelors of Arts in Mathematics from Reed College.
His paper, "Worth Weighting? How to think about and use weights in survey experiments", co-authored with Jasjeet Sekhon, Alexander Theodoridis, and Luis Campos, won the 2019 edition of the Warren Miller Prize, awarded by the Society of Political Methodology for the best work appearing in the journal Political Analysis in the preceeding year.
Some Selected Research Interests
- Applications in the social sciences with particular emphasis on political science, text data, and education.
- Principal Stratification (a method for causal analysis that incorporate post-treatment covariates)
- Heterogeneous treatment effects.
- Causal effect analysis.
- Analyzing data from randomized clinical trials.
- High-dimensional and sparse-regression methods.
- Non-parametric analysis of randomized experiments.
- Random effect models.
- Text summarization and key-phrase extraction.