Essays on Econometrics, Causal Inference, and Machine Learning
The traditional tools of econometrics may be inadequate for modern data sets, for example the 2020 US Census, which will be deliberately corrupted by the Census Bureau in the interest of privacy. Meanwhile, the modern tools of machine learning may be inadequate for the traditional goals of policy ev...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2023
|
| Online Access: | https://hdl.handle.net/1721.1/151478 https://orcid.org/0000-0001-9732-5001 |
| Summary: | The traditional tools of econometrics may be inadequate for modern data sets, for example the 2020 US Census, which will be deliberately corrupted by the Census Bureau in the interest of privacy. Meanwhile, the modern tools of machine learning may be inadequate for the traditional goals of policy evaluation, which are to measure cause and effect and to assess statistical significance.
In this dissertation, I develop tools for flexible causal inference, weaving machine learning into econometrics and solving unique problems that arise at their intersection. Specifically, I work in three domains at the intersection between econometrics and machine learning: (Chapter 1) causal inference with privacy protected data, (Chapter 2) rigorous statistical guarantees for machine learning, and (Chapter 3) simple algorithms for complex causal problems.
JEL: C81,C45,C26. |
|---|