Difference-in-Differences Estimators of Intertemporal Treatment Effects
Open accessThe DOI matches its Crossref record, with a small difference in title or year; 82 of the 82 references it cites were found in a registry or an index; 28 of the 40 sources its claims cite were checked for support.
Abstract
We study treatment-effect estimation using panel data. The treatment may be nonbinary, nonabsorbing, and the outcome may be affected by treatment lags. We make a parallel-trends assumption and propose event-study estimators of the effect of being exposed to a weakly higher treatment dose for ℓ periods. We also propose normalized estimators that estimate a weighted average of the effects of the current treatment and its lags. We also analyze commonly used two-way fixed-effects regressions. Unlike our estimators, they can be biased in the presence of heterogeneous treatment effects. A local-projection version of those regressions is biased even with homogeneous effects.
Overview
CoChat Summary
TL;DR
The paper develops difference-in-differences estimators for panel data where treatment can be nonbinary, nonabsorbing, and have lagged effects, without imposing homogeneous treatment effects. It proposes reduced-form and normalized event-study estimators plus a cost-benefit parameter, shows common TWFE dynamic regressions can be biased or contaminated, and revisits banking deregulation effects.
Key findings
- The proposed \(DID_\ell\) and normalized \(DID^n_\ell\) estimators are conditionally unbiased under no-anticipation and parallel trends conditional on the period-one treatment; \(DID^n_\ell\) estimates a weighted average of the current treatment and its first \(\ell-1\) lags, and a weighted sum of \(DID_\ell\)’s yields a cost-benefit parameter interpretable as an average total effect per unit of treatment.
- In a census of 100 highly cited AER papers from 2015–2019, 26 estimate TWFE regressions, but only four have a binary-and-staggered treatment; among the 20 non-binary/non-staggered papers, 11 estimate only static TWFE and nine estimate dynamic effects using intensity-period FE, local-projection, or distributed-lag regressions.
- The paper shows those three common TWFE dynamic methods may not estimate a convex combination of the paper’s \(\delta_{g,\ell}\) effects, may violate no-sign reversal, and local-projection panel regressions are contaminated by other exposure lengths and can be biased or wrong-signed even with constant effects.
- In the banking-deregulation application, local-projection coefficients are positive and significant through \(\ell=5\), insignificant at \(\ell=6,7,9\), and significantly negative at \(\ell=8\); the paper’s \(DID_1=0.043\) (s.e. \(0.035\)), \(DID_3=0.081\) (s.e. \(0.049\)), \(DID_5=0.148\) (s.e. \(0.064\)), placebos jointly insignificant (\(p=0.400\)), and the test that \(\ell \mapsto DID^n_\ell\) is constant is not rejected (\(p=0.328\)). For house prices, \(DID_1=0.003\) (s.e. \(0.004\)), \(DID_4=0.016\) (s.e. \(0.009\)), \(DID_5=0.026\) (s.e. \(0.010\)), and placebos are jointly insignificant (\(p=0.703\)).
Methods
- Panel of \(G\) groups observed over \(T\) periods, with dynamic potential outcomes allowing current outcomes to depend on current and lagged treatments; identifying assumptions include no anticipation, parallel trends for the status-quo outcome conditional on the period-one treatment, and a no-crossing condition, plus a design restriction requiring groups with the same period-one treatment and variation in first-treatment-change timing.
- Estimators compare switchers to not-yet-switchers with the same period-one treatment; the paper aggregates group-level \(DID_{g,\ell}\)’s into event-study effects, proposes normalized versions, placebo estimators, and asymptotic inference as \(G\to\infty\) under independent groups and regularity conditions, with confidence intervals conservative unless groups are i.i.d.
- Application revisits Favara and Imbs (2015) using 1994–2005 county-level banking deregulation data; treatment is the number of restrictions lifted (0–4); eight states never deregulate, 33 deregulate once, eight twice, and one three times; 38 of 42 deregulating states first do so in 1995–1998; \(DID_1\) and \(DID_8\) apply to 905 and 773 counties, respectively, and only three placebos apply to more than 50% of the 905 counties whose treatment changes at least once.
Limitations
- The paper states that the initial-conditions problem is not accounted for in the baseline notation; Assumption 1 rules out continuous period-one treatment, extremely non-persistent treatment, and no or universal treatment change; Assumption 4 may be implausible for some baseline-treatment values; \(\delta_\ell\)’s interpretation is complicated outside Design 1; \(\delta^n_\ell\) averages different lags and individual lag slopes are not estimable under Assumptions 3–4; cost-benefit analysis requires converting outcomes to monetary equivalents and assumes linear, non-stochastic treatment costs; inference is conservative in the i.n.i.d. setup unless groups are i.i.d.; and the local-projection issues are specific to the panel Regression 2, absent in time-series local projections and in Dube et al. (2023).
- The paper states placebos may fail to detect parallel-trends violations large enough to substantially bias \(DID_\ell\); in the application, only three placebos apply to more than 50% of the 905 counties, parallel trends can only be tested over three years whereas eight years are needed for \(DID_8\), loan-volume placebos are relatively large and imprecisely estimated, and \(DID_9\)–\(DID_{11}\) are not reported because they apply to small subsamples (357, 238, and 1 county).
- Evident from the text: several application estimates are imprecise (e.g., \(DID_1=0.043\) with s.e. \(0.035\); \(DID^n_1\) is much larger but imprecisely estimated); the paper proves weights sum to less than one in binary-and-staggered designs but only finds this in the non-binary/non-staggered application without a formal proof; and the design-conditional parameters may only partially uncover the structural function mapping current, lagged, and future treatments to outcomes.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
19 Valid · 10 Not valid · 7 Not checked · 214 Own results and interpretations
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“de Chaisemartin and D'Haultfœuille (2018) and de Chaisemartin and D'Haultfœuille (2020) had already noted that in a model assuming away effects of lagged treatments on the outcome, parallel trends across groups with different baseline treatments essentially rules out time-varying effects.”
What the sources say
- Partly supportedcites de Chaisemartin and D'Haultfœuille (2018) sourceExperimental — accuracy not yet measured
Section 2.2 says that the average treatment effect among units treated at baseline must be stable over time for the Wald-DID result. But it presents this as Assumption 4, separate from the common-trends Assumption 3; it does not say that parallel trends across groups with different baseline treatments itself rules out time-varying effects. Section 2.3 instead proposes an estimator that does not require that stability assumption. (LLM, conf=0.78)
- Disputedcites de Chaisemartin and D'Haultfœuille (2020) sourceExperimental — accuracy not yet measured
Split into 2 atoms — 1 confirmed, 0 partially supported, 1 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Checked by a reasoning model — may be wrong.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“DID 1 also reduces to the DID M estimator of de Chaisemartin and D'Haultfœuille (2020).”
What the sources say
- Supportedcites de Chaisemartin and D'Haultfœuille (2020) source
Section 4 (‘An alternative estimator’) defines DID_M as the authors’ estimator and describes it as a weighted average of the component DID estimators. The citation identifies the estimator to which the citing authors say DID_1 reduces; it does not attribute their reduction result to this source. (LLM, conf=0.90)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In non-binary and/or non-staggered designs, when all groups are untreated at period one, DID ℓ is equivalent to the estimator obtained by: 1. redefining the treatment as an indicator equal to one if group g has ever received a non-zero treatment at t , as Deryugina (2017) or Krolikowski (2018), among others, have done in their empirical analysis; 2. computing the estimator of θ es ( ℓ -1) of Calla”
What the sources say
- Partly supportedcites Callaway and Sant'Anna (2021) sourceExperimental — accuracy not yet measured
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
- Not checked — no full text of the sourcecites Deryugina (2017) source
- Supportedcites Krolikowski (2018) source
Split into 2 atoms — 2 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“In binary and staggered designs, our DID ℓ estimators reduce to the estimators of the event-study parameters θ es ( ℓ -1) of Callaway and Sant'Anna (2021), using not-yet-treated as controls.”
What the sources say
- Supportedcites Callaway and Sant'Anna (2021) source
Section 3.1.1 (page unavailable) defines Callaway and Sant’Anna’s event-study parameter θ_es(e), with event time e measured from treatment adoption. Section 2.3 (page unavailable) explicitly allows not-yet-treated groups as controls. The statement that the citing authors’ DID_l estimators reduce to those estimators is their own comparison, not a result attributed to this source. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“These findings differ sharply from those obtained by Favara and Imbs (2015).”
What the sources say
- Could not verifycites Favara and Imbs (2015) sourceExperimental — accuracy not yet measured
The cited paper’s Credit Supply and the Price of Housing section reports findings on the response of lending to branching deregulation. The citing sentence does not identify what “these findings” are, so our copy cannot establish whether they differ sharply from Favara and Imbs’s findings. (LLM, conf=0.76)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
140 more claims · 6 with their cited sources checked
Create a free account to see all 250 claims and every source verdict.
- It may state two separate claims as one. 52
- Probably not a substantial claim. 60
- Borderline: one of the tests for a substantial claim is unclear. 1
- The quote only partly states this claim. 2
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“I estimate Equation ( 1) using the estimator developed by de Chaisemartin and D'Haultfœuille (2026), hereafter dCDH, to accommodate the possibility that websites may re-allow the OAI-SearchBot crawler after having blocked it, causing the treatment status indicator, 𝐷𝐷 𝑖𝑖,𝑡𝑡 , to switch off.”
From Opting Out of Generative AI? Training Data, Search Visibility, and the Traffic Rankings of News Publishers (2026) · cites this paper as de Chaisemartin and D'Haultfœuille (2026)
In the citing paper
“The dCDH estimator, like many modern DID estimators, constructs counterfactual outcomes from untreated units and incorporates covariates within the estimation procedure rather than through a conventional regression specification.”
From Opting Out of Generative AI? Training Data, Search Visibility, and the Traffic Rankings of News Publishers (2026) · cites this paper as de Chaisemartin & D'Haultfœuille (2026)
In the citing paper
“The dCDH estimator, however, accommodates treatment reversals, so the baseline specification retains these websites in the sample.”
From Opting Out of Generative AI? Training Data, Search Visibility, and the Traffic Rankings of News Publishers (2026) · cites this paper as de Chaisemartin C, D'Haultfœuille X (2026)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 1.1 Placebo estimators
“One may have L pl = -1, if all groups that switch treatment do so for the first time at period 2.”
§ 1.1 Placebo estimators
“Then, let L pl = max g { min( T g -F g +1 , F g -2) } .”
Citations
Cites
How Much Should We Trust Differences-in-Differences Estimates?
Bertrand, M., Duflo, E., & Mullainathan, S. (2004) · The Quarterly Journal of Economics · doi:10.1162/003355304772839588 · Cited by 10,641
Mostly Harmless Econometrics: An Empiricist's Companion
Angrist, J. D., & Pischke, J.-S. (2009) · doi:10.1515/9781400829828 · Cited by 9,467
Difference-in-Differences with multiple time periods
Callaway, B., & Sant’Anna, P. H. C. (2021) · Journal of Econometrics · doi:10.1016/j.jeconom.2020.12.001 · Cited by 9,126
Difference-in-differences with variation in treatment timing
Goodman-Bacon, A. (2021) · Journal of Econometrics · doi:10.1016/j.jeconom.2021.03.014 · Cited by 8,046
Estimating dynamic treatment effects in event studies with heterogeneous treatment effects
Sun, L., & Abraham, S. (2021) · Journal of Econometrics · doi:10.1016/j.jeconom.2020.09.006 · Cited by 5,518
Mostly Harmless Econometrics: An Empiricist's Companion
Angrist, J. D., & Pischke, J.-S. (2008) · doi:10.2307/j.ctvcm4j72 · Cited by 5,051
Two-Way Fixed Effects Estimators with Heterogeneous Treatment Effects
de Chaisemartin, C., & D’Haultfœuille, X. (2020) · American Economic Review · doi:10.1257/aer.20181169 · Cited by 5,031
Self-citationEstimation and Inference of Impulse Responses by Local Projections
Jordà, Ò. (2005) · American Economic Review · doi:10.1257/0002828053828518 · Cited by 4,677
Identification and estimation of local average treatment effects
Imbens, G. W., & Angrist, J. D. (1994) · Econometrica · doi:10.2307/2951620 · Cited by 4,101
Robins, J. (1986) · Mathematical Modelling · doi:10.1016/0270-0255(86)90088-6 · Cited by 2,451
Cited by
Items 701–746 of 746
The Political U: New Evidence on the Economic Costs of Hybrid Regimes
Campos, N. F., Coricelli, F. R., & Frigerio, M. (2026) · Economics and Politics · doi:10.1111/ecpo.70052
Global Value Chains and Political Tension: The Case of Korean Firms
Gwon, G. (2026) · The B E Journal of Macroeconomics · doi:10.1515/bejm-2025-0001
Religious Participation After Covid‐19: Evidence From US Catholic Dioceses and Smartphone Data
Cools, A., Carlos Esparza, S. J., & Park, J. (2026) · Journal for the Scientific Study of Religion · doi:10.1111/jssr.70067
Mafia Infiltration and Political Participation
GASPARRONI, A., & Ubaldi, M. (2026) · The B E Journal of Economic Analysis & Policy · doi:10.1515/bejeap-2026-0043
Paving the Green Tracks: The Dual Impacts of Heavy-haul RailwaysPreprint
Zhang, Q., Chen, K., Feng, S., Tan, Y., & Zhai, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6945366
China’s one-child exemptions and the spousal age gap
Gao, J., Park, M. S., & POLACHEK, S. W. (2026) · Review of Economics of the Household · doi:10.1007/s11150-026-09864-y
The Spatial Impact of Judicial Administration on Firms' Performance
Sessa, V. (2026) · Labour · doi:10.1111/labr.70019
Do China's State‐Owned Enterprises Promote Their Suppliers' Participation in Global Value Chains?
Huang, Y., & Li, X. (2026) · World Economy · doi:10.1111/twec.70091
Liu, M., & Schut, R. A. (2026) · Health Services Research · doi:10.1111/1475-6773.70147
Wei, Y., Qu, Y., Bao, K., et al. (2026) · Frontiers in Environmental Science · doi:10.3389/fenvs.2026.1881710
Anticipation vs. Reality: The Dynamics of Transmission Line Impacts on Property Values
Gangadhar, S. S. B., Hoffmann, C., & Müsgens, F. (2026) · International Conference on the European Energy Market (EEM) · doi:10.1109/eem68581.2026.11589755
Stigler, M., Grabs, J., Heilmayr, R., Carlson, K. M., Chandra, A., Benedict, J. J., & Garrett, R. D. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2511503123 · Cited by 3
Departmentalized instruction and elementary school effectiveness
Backes, B., Cowan, J., & Goldhaber, D. D. (2026) · Journal of Public Economics · doi:10.1016/j.jpubeco.2026.105715
Technical Change Through Global Value Chains: Evidence From Firms Worldwide
Ledezma, I., & López‐Villavicencio, A. (2026) · World Economy · doi:10.1111/twec.70126
The uncertainty of risk preferences – a case study of storms and floods in Germany
Grüner, S., & Zwies, F. (2026) · Applied Economics Letters · doi:10.1080/13504851.2026.2705675
Profitability of Open-Source Software Product Development
Singh, S. P., Ramasubbu, N., Kemerer, C. F., & Hydari, M. Z. (2026) · Information Systems Research · doi:10.1287/isre.2025.1821
AI innovation and labor market polarization: Evidence from European regions
Minniti, A., Klaus Prettner, A., & Venturini, F. (2026) · Economics Letters · doi:10.1016/j.econlet.2026.113180
Renault, T., Bergeaud, A., & Bosquet, C. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2618638123 · Cited by 1
Gao, H., Wang, Z., Zhang, B., & Meng, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7290478
Pandemic disruptions in global supply chains: Evidence on trade values and prices from French firms
Brussevich, M., Papageorgiou, C., & Wibaux, P. (2026) · Canadian Journal of Economics/Revue canadienne d économique · doi:10.1111/caje.70082
Unintentional man‐made disasters, risk preferences, and insurance demand
Chen, Z., Fang, M., Qiu, J., & Xu, R. (2026) · Journal of Risk & Insurance · doi:10.1111/jori.70071
The effects of university-industry collaboration subsidies on firm performance
Palangkaraya, A., Paul, J., Russell, T., & Elisabeth, W. (2026) · Industrial and Corporate Change · doi:10.1093/icc/dtag050 · Cited by 1
Financial Sanctions and Bank Stability over TimePreprint
Lv, J., Xu, R., & Cai, X. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7329428
Wang, J., Zhou, Z., Qu, H., et al. (2026) · Forests · doi:10.3390/f17091018
Kirkland, J. H., & Shea, P. E. (2026) · Regulation & Governance · doi:10.1111/rego.70203
AI innovation policy and corporate digital transformation: Evidence from China
Zhang, C., & Fan, H. (2026) · Technology in Society · doi:10.1016/j.techsoc.2026.103531
Payroll taxes, firm dynamism, and aggregate productivity
Feng, J., Li, Y., & Liu, Y. (2026) · Journal of Development Economics · doi:10.1016/j.jdeveco.2026.103918
A New Expanded Dataset to Study Refugee Camps in Sub-Saharan Africa 1999–2024
Anti, S., Salemi, C., Rigberg, J., Leopold, S., Silva, K., & Hoogeveen, J. G. (2026) · The World Bank Economic Review · doi:10.1093/wber/lhag033
Does the “Zero-Waste City” Policy Improve Urban Land Green Use Efficiency? Evidence from China
Zhang, M., Xu, S., Wu, Y., & Yang, T. (2026) · Land · doi:10.3390/land15091644
Ee, M. S., Li, T., & Lu, C. (2026) · Economics and Politics · doi:10.1111/ecpo.70068
Insurgency and erosion of public confidence in the Islamic Republic of Afghanistan
Mobariz, A. S., & Murtazashvili, I. (2026) · Defence and Peace Economics · doi:10.1080/10242694.2026.2729329
How Do Savings Groups Respond to Agricultural Shocks?
van Hemert, D., D’Espallier, B., & Mersland, R. (2026) · Journal of Agricultural Economics · doi:10.1111/1477-9552.70083
Fueling green innovation: How climate policy reshapes corporate capital structure
Chang, X., Xie, Y., & Xu, W. (2026) · Journal of Innovation & Knowledge · doi:10.1016/j.jik.2026.101162 · Cited by 1
Wang, Y., Xia, Y., Cai, C., Shi, Z., & He, P. (2026) · International Journal of Epidemiology · doi:10.1093/ije/dyag209
Financial sanctions and bank asset quality: does persistence matter?
Lv, J., Xu, R., & Cai, X. (2026) · Finance research letters · doi:10.1016/j.frl.2026.110834
Bank-firm digital synergy in credit relationships: Evidence from corporate leverage manipulation
Lu, Y., & Wang, Y. (2026) · Finance research letters · doi:10.1016/j.frl.2026.110836
When Do Realised Losses Become Subjective Economic Insecurity? Evidence from Cyclone Ana in MalawiPreprint
Cesar, R. G. (2026) · Research Square · doi:10.21203/rs.3.rs-10593107/v1
Measuring Merger Effects with Revenue Data
Hess, J. T., & Wang, X. (2026) · Documentos de trabajo/Documento de trabajo - Banco de España, Servicio de Estudios · doi:10.53479/44445
Gone With the Wind: Tornadoes and Local Wealth in the United States
Corvasce, A. (2026) · The B E Journal of Economic Analysis & Policy · doi:10.1515/bejeap-2026-0164
Lai, A., Wu, J., Cao, Y., & Lin, T. (2026) · Environmental Impact Assessment Review · doi:10.1016/j.eiar.2026.108754
The Influence of Climate Initiatives on Capital Structure: The Green Halo Effect
Ramos-García, D., López-Martín, C., & Sanz, R. A. (2026) · International Journal of Finance & Economics · doi:10.1002/ijfe.70309
R&D tax credits across the EU: nonsense or common sense? A dynamic panel data approach
Jacquet, L., & Robin, S. (2026) · Economics of Innovation and New Technology · doi:10.1080/10438599.2026.2732164
Devour the future: Locust plagues and educational disruption in Ethiopia
Yan, J.-L. (2027) · Journal of Environmental Economics and Management · doi:10.1016/j.jeem.2026.103434
Terrorism and altruistic giving: Evidence from child sponsorship
Posso, A., & Feeny, S. (2026) · Journal of Development Economics · doi:10.1016/j.jdeveco.2026.103951
The Heterogeneous Effect of the Italian Special Economic Zones on Firms: A Regional Analysis
Amaddeo, E., Bergantino, A. S., & Fusco, G. (2026) · Journal of Regional Science · doi:10.1111/jors.70100
Metadata
- Authors
- de Chaisemartin, C., & D’Haultfœuille, X.
- Affiliations
- Sciences Po Paris, Economics Department
- Centre de Recherche en Économie et Statistique (FR)
- Venue
- Review of Economics and Statistics
- Publisher
- MIT Press
- Published
- 2026-07
- Volume
- 108
- Issue
- 4
- Pages
- 863-880
- ISSN
- 0034-6535 (ISSN-L)
- 1530-9142
- OpenAlex
- W3041109582
- Cited by
- 740
- References
- 81
- Citations by year
- 2026: 147
- FWCI
- 63.78
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Locations
- The Review of Economics and Statistics (publishedVersion)
- SSRN Electronic Journal (publishedVersion)
- National Bureau of Economic Research (publishedVersion)
- SSRN Electronic Journal (acceptedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion, cc-by-nc-nd)
- HAL (submittedVersion, cc-by-nc)
- HAL (submittedVersion)
- arXiv (Cornell University)
- Funders
- European Commission
- Agence Nationale de la Recherche (ANR-17-CE26-0015, ANR-17)
- HORIZON EUROPE European Research Council (101043899)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Spatial and Panel Data Analysis
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Keywords
- difference-in-differences, parallel trends assumption, treatment effect heterogeneity, two-way fixed effects, local projections, panel data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-29, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
