The Consequences of Mismeasuring Economic Activity
ERC Starting Grant "MEImpact"
Motivation
Measuring economic activity is a fundamental challenge for empirical work in economics. Most empirical projects raise concerns about whether the data do in fact measure what they purport to measure. Mismeasurement may lead to severe model misspecification, biased estimates, and misled conclusions and policy decisions. Unfortunately, formally accounting for the possibility of mismeasurement in the econometric model is complicated and possible only under strong assumptions that limit the credibility of resulting conclusions. Therefore, the most common approaches to measurement issues are to ignore them, to informally argue why they may not be of first-order importance, to abandon the project, or to search for better data.
Objective
The objective of this research project is to develop new methodologies for formally assessing the potential impact of measurement error (ME) on all aspects of an empirical project: on model-building, on estimation and inference, and on decision-making. For instance, the new inference procedures allow the researcher to test whether ME is a statistically significant feature that should be modeled, whether ME distorts objects of interest (e.g. a production or utility function), whether ME distorts conclusions from hypothesis tests, and whether ME affects subsequent decision-making.
We show that answering such questions is possible under much weaker assumptions than identification and estimation of a ME model and thus leads to more credible and robust conclusions. In addition, the implementation of the new procedures can be based on standard nonparametric estimation techniques that are part of many applied researchers’ toolkits.
Publications
- Optimally-Transported Generalized Method of Moments
Susanne Schennach and Vincent Starck
Econometrica, 2026 - Finite- and large-sample inference for ranks using multinomial data with an application to ranking political parties
S. Bazylik, M.Mostad, J.P. Romano, A. Shaikh, and Daniel Wilhelm
Journal of Econometrics, 2025 - Powerful t-Tests in the Presence of Nonclassical Measurement Error
Dongwoo Kim and Daniel Wilhelm
Econometric Reviews, 2024 - Inference for Ranks with Applications to Mobility across Neighbourhoods and Academic Achievement across Countries
M.Mostad, J.P. Romano, A. Shaikh, and Daniel Wilhelm
Review of Economic Studies, 2024 - A Comment on: "Invidious Comparisons: Ranking and Selection as Compound Decisions" by Jiaying Gu and Roger Koenker
M.Mostad, J.P. Romano, A. Shaikh, and Daniel Wilhelm
Econometrica, 2023 - Statistical uncertainty in the ranking of journals and universities
M.Mostad, J.P. Romano, A. Shaikh, and Daniel Wilhelm
AEA Papers and Proceedings, 2022
Working Papers
- A Powerful Bootstrap Test of Independence in High Dimensions
Mauricio Olivares, Tomasz Olma, and Daniel Wilhelm
2026 - Inference for Rank-Rank Regressions
Denis Chetverikov and Daniel Wilhelm
conditionally accepted at Econometrica, 2025 - Using spatial modeling to address covariate measurement error
Susanne Schennach and Vincent Starck
conditionally accepted at the Journal of Econometrics, 2025 - Flexible Covariate Adjustments in Regression Discontinuity Designs
Claudia Noack, Tomasz Olma, and Christoph Rothe
2025 - csranks: An R Package for Estimation and Inference Involving Ranks
D. Chetverikov, M. Mogstad, P. Morgen, J.P. Romano, A. Shaikh, and Daniel Wilhelm
2024
Non-Technical Summaries
- Finite- and Large-Sample Inference for Ranks using Multinomial Data with an Application to Ranking Political Parties
BFI Research Brief - Inference for Ranks with Applications to Mobility across Neighborhoods and Academic Achievements across Countries
BFI Research Brief
Stone Centre non-technical summary
High-Profile Applications of the New Methods
Software
- R package csranks implementing statistical methods for inference on ranks and on rank-rank regressions
- R package METests implementing tests for the presence of measurement error:
- R package hdIndep implementing tests of independence in high-dimensions