Avidit Acharya, Jens Hainmueller, Yiqing Xu
arXiv 12 Apr 2026 · Statistics — Methodology
arXiv:2604.10845 · PDF · DOI · OpenAlex · Extracted main text
Conjoint experiments randomize multidimensional profiles, offering a powerful design for recovering structural preference parameters -- including marginal rates of substitution, willingness to pay, and the distribution of preferences across a population. Yet the dominant approach in political science has focused on nonparametric causal estimands that do not leverage this potential. We propose a structural approach that embeds a deep neural network within a random utility logit model, allowing preference parameters to vary as a fully flexible function of respondent characteristics. The neural network addresses the concern that a parametric specification may not capture the true data generating process, while double/debiased machine learning provides valid inference on average preference parameters. We apply our method to three prominent conjoint studies and find rich preference heterogeneity masked by reduced-form averages: a near-zero gender effect coexists with 83% preferring female candidates, opposition to undemocratic behavior is near-universal but varies sharply in intensity, and progressive tax preferences cut across every partisan subgroup.
appendix boundary found by appendix_command · 88% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Ballard-Rosa, Cameron and Martin, Lucy and Scheve, Kenneth (2017) The Structure of American Income Tax Policy Preferences | 0.961 | 9 | 3 | 89% |
| 2 | Graham, Matthew H. and Svolik, Milan W (2020) Democracy in America? Partisanship, Polarization, and the Robustness of Support for Democracy in the United States | 0.950 | 7 | 3 | 86% |
| 3 | Saha, Shom and Weeks, Jessica L. P (2022) Welfare Over Democracy? State Capacity Signals and Self-Interested Voting | 0.928 | 5 | 4 | 80% |
| 4 | Abramson, Scott F. and Ko cak, Korhan and Magazinnik, Asya (2022) What Do We Learn about Voter Preferences from Conjoint Experiments? | 0.928 | 4 | 3 | 100% |
| 5 | Hainmueller, Jens and Hopkins, Daniel J. and Yamamoto, Teppei (2014) Causal Inference in Conjoint Analysis: Understanding Multidimensional Choices via Stated Preference Experiments self | 0.874 | 5 | 2 | 100% |
| 6 | Bansak, Kirk and Hainmueller, Jens and Hopkins, Daniel J. and Yamamo… (2023) Using Conjoint Experiments to Analyze Election Outcomes: The Essential Role of the Average Marginal Component Effect self | 0.843 | 5 | 3 | 60% |
| 7 | Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Du… (2018) Double/Debiased Machine Learning for Treatment and Structural Parameters | 0.737 | 3 | 2 | 100% |
| 8 | Farrell, Max H. and Liang, Tengyuan and Misra, Sanjog (2025) Deep Learning for Individual Heterogeneity: An Automatic Inference Framework | 0.737 | 3 | 2 | 100% |
| 9 | McFadden, Daniel (1974) Conditional Logit Analysis of Qualitative Choice Behavior | 0.737 | 3 | 2 | 100% |
| 10 | Green, Paul E. and Srinivasan, V (1990) Conjoint Analysis in Marketing: New Developments with Implications for Research and Practice | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 37 scored citations.