The heterogeneous impact of the EU-Canada agreement with causal machine learning
Bibliographic record
Abstract
This paper introduces a causal machine learning approach to investigate the effects of free trade agreements and applies it to the EU-Canada Comprehensive Economic and Trade Agreement (CETA). Previous estimates of the impact of trade liberalization have been found to be unstable and contradictory, possibly due to the presence of heterogeneous treatment effects. The matrix completion estimator computes multidimensional counterfactuals in trade data at the firm, product, and destination levels. Compared with other estimators, it relies on a weaker exogeneity assumption and a more general functional form. In the case of CETA, we obtain both positive and negative idiosyncratic treatment effects at the product-destination level, although the sales-weighted average treatment effect is 6.4% in the year after the agreement. At the same time, we can estimate idiosyncratic treatment effects for the extensive margin at the product-destination level; thus, we find product churning beyond regular entry-exit dynamics: 8.1% that were not previously exported, and about 7.3% that are no longer exported. Finally, we consider the case of multiproduct firms after ranking product portfolios. After CETA, we observe a reallocation of French exports toward the first and most exported products, possibly driven by increased competition in the local market by other European producers after trade liberalization.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.034 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".