Beyond Linearity: Semiparametric Solutions to Contamination Bias with Multi-valued Treatments
Abstract
We examine semiparametric solutions to contamination bias for nonbinary treatments. Deepening the discussion by Goldsmith-Pinkham et al. (2024), we detail how spline functions approximate conditional expectation and propensity score functions under weak functional-form assumptions. Reanalyzing 18 regressions across 11 studies, we compare standard linear regressions against parametric and semiparametric versions of three contamination-robust estimators. We document large point-estimate discrepancies between parametric and semiparametric approaches and find that adopting flexible semiparametric solutions may not increase statistical uncertainty substantially. We recommend that researchers verify the robustness of their conclusions to the use of semiparametric tools that address contamination bias.
Related
- Learning and Control Beyond Linearity: Towards a Non-asymptotic Theory for Bilinear Systems
- Computer-assisted proofs of periodic solutions of state-dependent delay equations beyond perturbative regimes
- Naked Singularities beyond Spherical Symmetry: Instability of κ-Self-Similar Solutions via an Iteration Scheme
- Towards a unified theory for semiparametric data fusion with individual-level data
- Linearity of Graph Manifold Groups
BibTeX
@misc{finger2026beyond,
title = {{Beyond Linearity: Semiparametric Solutions to Contamination Bias with Multi-valued Treatments}},
author = {Michel Csillag Finger and Vitor Possebom},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.20473},
eprint = {2609.20473},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.20473},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Beyond Linearity: Semiparametric Solutions to Contamination Bias with Multi-valued Treatments
AU - Michel Csillag Finger
AU - Vitor Possebom
PY - 2026
DA - 2026/09/17
PB - arXiv
DO - 10.48550/arxiv.2609.20473
UR - https://arxiv.org/abs/2609.20473
AB - We examine semiparametric solutions to contamination bias for nonbinary treatments. Deepening the discussion by Goldsmith-Pinkham et al. (2024), we detail how spline functions approximate conditional expectation and propensity score functions under weak functional-form assumptions. Reanalyzing 18 regressions across 11 studies, we compare standard linear regressions against parametric and semiparametric versions of three contamination-robust estimators. We document large point-estimate discrepancies between parametric and semiparametric approaches and find that adopting flexible semiparametric solutions may not increase statistical uncertainty substantially. We recommend that researchers verify the robustness of their conclusions to the use of semiparametric tools that address contamination bias.
ER -