![Quantitative Economics logo](/images/qe.gif)
Quantitative Economics
Journal Of The Econometric Society
Edited by: Stéphane Bonhomme • Print ISSN: 1759-7323 • Online ISSN: 1759-7331
Edited by: Stéphane Bonhomme • Print ISSN: 1759-7323 • Online ISSN: 1759-7331
Quantitative Economics: May, 2024, Volume 15, Issue 2
https://doi.org/10.3982/QE2354
p. 279-330
Yuehao Bai, Jizhou Liu, Max Tabord‐Meehan
This paper studies inference in randomized controlled trials with multiple treatments, where treatment status is determined according to a “matched tuples” design. If there are possible treatments, then by a matched tuples design, we mean an experimental design where units are sampled i.i.d. from the population of interest, grouped into “homogeneous” blocks of size , and finally, within each block, exactly one individual is randomly assigned to each of the treatments. We first study estimation and inference for matched tuples designs in the general setting where the parameter of interest is a vector of linear contrasts over the collection of average potential outcomes for each treatment. Parameters of this form include standard average treatment effects used to compare one treatment relative to another, but also include parameters that may be of interest in the analysis of factorial designs. We first establish conditions under which a sample analog estimator is asymptotically normal and construct a consistent estimator of its corresponding asymptotic variance. Combining these results establish the asymptotic exactness of tests based on these estimators. In contrast, we show that, for two common testing procedures based on t‐tests constructed from linear regressions, one test is generally conservative while the other is generally invalid. We go on to apply our results to study the asymptotic properties of what we call “fully‐blocked” 2K factorial designs, which are simply matched tuples designs applied to a full factorial experiment. Leveraging our previous results, we establish that our estimator achieves a lower asymptotic variance under the fully‐blocked design than that under any stratified factorial design, which stratifies the experimental sample into a finite number of “large” strata. A simulation study and empirical application illustrate the practical relevance of our results.
Yuehao Bai, Jizhou Liu, and Max Tabord-Meehan
Supplemental Appendix
Yuehao Bai, Jizhou Liu, and Max Tabord-Meehan
The replication package for this paper is available at https://doi.org/10.5281/zenodo.10601297. The Journal checked the data and codes included in the package for their ability to reproduce the results in the paper and approved online appendices.
March 5, 2024
The terms of the Editors of the Econometric Society's three journals end June 30, 2025. We are pleased to announce the incoming Editors and to thank the outgoing Editors for their excellent and continuing service.
Econometrica: Since 2019, Guido Imbens has served as the 14th Editor of Econometrica. On July 1, 2025, Marina Halac will become the Editor.
Quantitative Economics: Stéphane Bonhomme has been the Editor of Quantitative Economics since 2021. His successor will be Bernard Salanié.
Theoretical Economics: The Editor of Theoretical Economics since 2021 has been Simon Board. Taking over for him in July 2025 will be Federico Echenique.
Guido, Stéphane, and Simon have been outstanding Editors. We are grateful to them for the work they have done and will continue to do, and we look forward to further congratulating them next year. We believe Marina, Bernard, and Federico will be outstanding successors and we thank them in advance for their service.
Finally, we are grateful to Larry Samuelson for chairing all three search committees, and we thank the search committee members for their hard and fruitful work:
Econometrica: Christian Dustmann, Lars Hansen, Alessandro Lizzeri, George Mailath, Ariel Pakes, Helene Rey, and Elie Tamer.
QE: Kate Ho, Michael Keane, Felix Kubler, Whitney Newey, and Frank Schorfheide.
TE: Jeff Ely, Johannes Horner, Gilat Levy, Meg Meyer, and Ran Spiegler.