AJPS paper finds measurement error in 8 conjoint studies and proposes a correction
RobbWiller · x · 2026-07-24
New AJPS paper proposes a correction for measurement error in conjoint studies
The paper, "Correcting measurement error bias in conjoint survey experiments," appears in AJPS and is coauthored by Katherine Clayton, Yusaku Horiuchi, Aaron R. Kaufman, Gary King, and Mayya Komisarchik.
- The authors replicate the data collection and analysis from eight prominent conjoint studies and find substantial measurement error in all of them, despite successfully reproducing the published results.
- They identify a common empirical pattern in how this error shows up across conjoint designs.
- Based on that pattern, they introduce an easy-to-use statistical method to correct the bias.
- They also argue for a simpler and more powerful framework for designing, organizing, understanding, and analyzing conjoint data.
More from Research
- Photon-1 learns computer use from 18 years of unlabeled screen recordings — ycombinator · 2026-07-24
- New gel may regrow tooth enamel, according to a ScienceDaily report — SnoozeDoggyDog · 2026-07-24
- Why not build a small specialist model instead of a large MoE? — exaknight21 · 2026-07-24
- Hong Wang’s NeurIPS paper tightened low-rank approximation bounds with interpolation — 量子位 · 2026-07-24
- New study says multi-agent systems only help when compressed handoffs keep all key context — rohanpaul_ai · 2026-07-24
- Robot world model trained on 15 hours of video generalizes to unseen bodies — jon_barron · 2026-07-24