Lea Bottmer

Photo by Vanessa Coleman

Welcome!

I am a PhD candidate in Economics at Stanford University. Prior to Stanford, I received my BSc and MSc from Maastricht University in Econometrics and Operations Research.

My research interests are in econometrics and causal inference. My current projects focus mostly on methods for panel data settings. I am fortunate to be advised by Guido Imbens and Jann Spiess.

I am on the academic job market in 2025-26.

You can find my CV here.

You can contact me at lbottmer@stanford.edu.

Research

Work in Progress

Synthetic Control with Disaggregated Data (Job Market Paper)

[Python package]

Abstract: The synthetic control estimator is widely used to evaluate aggregate-level policies, but researchers increasingly face settings with rich, disaggregated data (e.g., county-level outcomes within states) that raise new questions about aggregation choice. Existing approaches incorporate such data by estimating separate synthetic controls for each disaggregated treated unit, enlarging the donor pool with disaggregated control units, or both. These strategies can improve fit but also amplify noise, with little guidance on how to balance these trade-offs. This paper develops a general framework for synthetic control with disaggregated data that nests the classical synthetic control estimator and other existing approaches. Within this framework, I propose a multi-level SC (mlSC) estimator that formalizes the aggregation choice as a data-driven regularization problem. The estimator flexibly regularizes toward the classical synthetic control estimator while exploiting additional variation from the disaggregated data. In simulations calibrated to four empirical settings, mlSC matches or outperforms existing approaches. Two applications—Minnesota’s cigarette tax and minimum wage effects on teen employment—illustrate its practical value.

From Policy Evaluation to Generalization: A Framework Using Synthetic Control

Abstract: Many real-world policy decisions depend not only on understanding the effects of past interventions but also on predicting how existing policies would perform in new settings. While the policy evaluation literature has grown rapidly over the past three decades — both methodologically and empirically —relatively little work takes the forward-looking perspective. This paper aims to provide insights into one one part of this open question: What would happen if we implemented the same policy for a different unit? In this paper, I propose a synthetic control-based approach that re-imagines the synthetic control (SC) estimator as a tool for treatment effect prediction rather than retrospective evaluation. The approach relies on leveraging disaggregated data of the treated unit and yields two estimators of interest: (1) using estimated treatment effects, double SC estimator, or (2) using outcomes of the treated unit directly. I argue that the double SC estimator, which focuses on treatment effects, is the more intuitive approach. The double SC estimator uses two sets of weights, one for the treated disaggregated unit and one for the larger donor pool.

Unbiased Covariate Adjustments in Clustered Experiments (with Jann Spiess, Daniel Watt and Jason Weitze)

Abstract: Recent work has demonstrated the value of flexibly incorporating covariates when analyzing experiments with many experimental units. It is less clear how or even if we should incorporate covariate information in settings with few experimental units like clustered experiments. For this case, we propose a Leave One or Two Cluster Out (LOCO) estimator that leverages the cluster-level randomization to guarantee an unbiased estimate while simultaneously incorporating individual-level information in a flexible way to reduce variance. While clustered experiments tend to have few experimental units, e.g. villages, we often observe outcome data and covariates for a much larger number of individuals, e.g. people living in those villages. In practice researchers often choose between leveraging this more granular data in individual-level linear regressions that control for covariates and a simple difference in means that ignores the covariates. While the former reduces variance, it comes at the expense of the latter's unbiasedness guarantee. Our proposed estimator aims to combine the best of both strategies.

Publications

A Design-Based Perspective on Synthetic Control Methods (with Guido Imbens, Jann Spiess and Merrill Warnick), Journal of Business and Economic Statistics, 2024

Sparse Regression for Large Data Sets with Outliers (with Christophe Croux and Ines Wilms), European Journal of Operational Research, 2022

Teaching

I am passionate about teaching econometrics and data science, helping students build strong theoretical foundations and practical skills. My goal is to create an engaging and supportive learning environment where students can develop the confidence to apply complex methods to real-world problems.

Teaching Awards & Recognition

Centennial Teaching Assistant Award (2025)

Stanford University, School of Humanities and Sciences

Outstanding Teaching Assistant Award (3-time recipient: Winter 25, Spring 24, Spring 23)

Stanford University, Department of Economics

Preparing Future Teaching Professors Fellow (2024-2025)

Stanford University & West Valley College, Mentor: Professor Sam Liu

Teaching Publications

An Undergraduate Course in Causality (with Guido Imbens, Jason Weitze and Mary Wootters), Harvard Data Science Review, forthcoming

Teaching Materials

ECON 102B: Applied Econometrics

Stanford University | Undergraduate Level | Spring 2025