Machine-learning estimates connect campaign spending effects to possible shifts in congressional control
Source check: Source checked. Not independent scientific confirmation.
Finding: The authors used flexible machine-learning estimates of heterogeneous campaign-spending effects and aggregated them across U.S. House and Senate elections. They report nonlinear marginal effects at the campaign level and counterfactual seat swings that could have changed party control at historically observed spending levels; such conditions appear less common in the last decade. These are model-based observational counterfactuals and do not prove that spending causally determines election outcomes.
Technology: Flexible machine-learning estimation of heterogeneous campaign-spending effects
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Flexible machine-learning models estimate heterogeneous, nonlinear campaign-spending effects that are aggregated to the congressional level.
- Test and result
- The primary paper reports robustness analyses across alternative machine-learning methods and counterfactual aggregation of estimated campaign-level spending effects to congressional seat totals.
- Limitation / still unknown
- The analyses are observational counterfactual estimates and do not establish that campaign spending causally determines election outcomes.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://doi.org/10.1371/journal.pone.0305846
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Full primary publisher article, including Methods, Results, author affiliations and publication history.
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.