An Averaging Alternative to Pre-Trend Testing
Abstract
We study difference-in-differences (DID) estimation of average treatment effects on the treated when the researcher is uncertain about which pre-treatment periods satisfy the parallel trends assumption. Roth (2022) shows that pre-trend testing can induce bias, complementing the statistical literature on post-selection inference. We propose the model averaged difference-in-differences (MADID) estimator, a weighted average of the candidate 2×2 DID estimators. The weights are normalized exponential functions of the candidate residual sums of squares, so implementation requires no specification test. We derive MADID's asymptotic properties under conditions that make invalid comparisons detectably more variable than at least one valid comparison. Under these conditions, MADID is consistent when the parallel trends assumption holds for at least one pre-treatment period. Although its joint limiting distribution across post-treatment periods is generally non-Gaussian, inference can be conducted by subsampling or simulation.
Related
- Food-System Stress Testing: Prediction Tasks Under Alternative Outcome Definitions
- Unique equivariant pseudo expectation and generalized Powers averaging for crossed product
- end point estimates for the bilinear circular averaging operator
- Dimensionality-induced critical phase transition in stochastic Lotka-Volterra equation: From statistical averaging to systemic tipping point
- Averaging principles for nonautonomous multiscale stochastic Burgers equations with reflection
BibTeX
@misc{brown2026averaging,
title = {{An Averaging Alternative to Pre-Trend Testing}},
author = {Nicholas L. Brown and Qiushi Bu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.05705},
eprint = {2610.05705},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.05705},
}
RIS
TY - UNPB
TI - An Averaging Alternative to Pre-Trend Testing
AU - Nicholas L. Brown
AU - Qiushi Bu
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2610.05705
UR - https://arxiv.org/abs/2610.05705
AB - We study difference-in-differences (DID) estimation of average treatment effects on the treated when the researcher is uncertain about which pre-treatment periods satisfy the parallel trends assumption. Roth (2022) shows that pre-trend testing can induce bias, complementing the statistical literature on post-selection inference. We propose the model averaged difference-in-differences (MADID) estimator, a weighted average of the candidate 2×2 DID estimators. The weights are normalized exponential functions of the candidate residual sums of squares, so implementation requires no specification test. We derive MADID's asymptotic properties under conditions that make invalid comparisons detectably more variable than at least one valid comparison. Under these conditions, MADID is consistent when the parallel trends assumption holds for at least one pre-treatment period. Although its joint limiting distribution across post-treatment periods is generally non-Gaussian, inference can be conducted by subsampling or simulation.
ER -