When Is Parallel Trends Sensitive to Functional Form?
The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index; 2 of the 10 sources its claims cite were checked for support.
Abstract
This paper assesses when the validity of difference‐in‐differences depends on functional form. We provide a novel characterization: the parallel trends assumption holds under all strictly monotonic transformations of the outcome if and only if a stronger “parallel trends”‐type condition holds for the cumulative distribution function of untreated potential outcomes. This condition for parallel trends to be insensitive to functional form is satisfied if and essentially only if the population can be partitioned into a subgroup for which treatment is effectively randomly assigned and a remaining subgroup for which the distribution of untreated potential outcomes is stable over time. These conditions have testable implications, and we introduce falsification tests for the null that parallel trends is insensitive to functional form.
Overview
CoChat Summary
## TL;DR
The paper characterizes exactly when the parallel trends assumption in difference-in-differences is insensitive to outcome transformations: this happens if and only if a corresponding parallel-trends condition holds for the untreated outcome distributions’ CDFs. It also shows this condition is satisfied only in special cases, including random assignment, stationary untreated outcomes, or a mixture of the two.
## Key findings
- Parallel trends is invariant to strictly monotonic transformations if and only if a parallel-trends-type condition holds for the CDFs of untreated potential outcomes.
- The paper characterizes this invariance as essentially requiring one of three structures:
1. treatment is as-if randomly assigned,
2. untreated outcome distributions are stable over time within each group, or
3. a hybrid mixture of the first two cases.
- The authors show the CDF-based condition has testable implications: when the outcome has finite support, the null can be tested by checking whether the implied distribution has non-negative mass at all support points.
- In the minimum-wage illustration using Cengiz et al. (2019), the implied counterfactual density is negative for wages around roughly $5–7/hour in the 2007–2015 comparison, and the null that all implied densities are positive is rejected with p < 0.001; for the 2010–2015 comparison, the null is not rejected (p = 0.29).
## Methods
- The paper develops a two-period canonical difference-in-differences model with treated and comparison populations, no anticipatory effects, and untreated potential outcomes indexed by group and time.
- It proves a characterization result linking invariance of parallel trends under all strictly monotonic transformations to a distributional parallel-trends condition for untreated potential outcomes, plus a decomposition result showing when that condition can hold.
- For empirical testing, it proposes falsification tests based on whether the implied counterfactual distribution is weakly increasing; in the illustration, the authors use state-level minimum-wage and employment-to-population-ratio data from Cengiz et al. (2019) and bootstrap-based moment-inequality testing.
## Limitations
- The paper states that failing to reject the null does not imply parallel trends is insensitive to functional form; this is a limitation of the proposed tests.
- It also warns that relying on such tests may create pre-testing problems, analogous to issues in pre-trends testing.
- Evident from the text: the main characterization is developed for a two-period model, with extensions only noted as immediate implications for multi-period, staggered-adoption, and conditional parallel-trends settings rather than worked out in detail.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
2 Valid · 1 Not valid · 5 Not checked · 17 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The validity of this analysis requires parallel trends throughout the birth weight distribution - precisely the condition that Proposition 3.1 shows is needed for the usual parallel trends assumption to be insensitive to functional form.”
What the sources say
- Partly supportedcites Almond, Hoynes and Schanzenbach (2011) sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 1 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.
- Partly supported
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Proposition 3.2. Suppose that the distributions Y it p 0 q| D i d for all d, t P t 0 , 1 u have a Radon-Nikodym density with respect to a common dominating, positive σ -finite measure. Then parallel trends is invariant to transformations if and only if there exists θ P r 0 , 1 s and CDFs G t p q and H d p q depending only on time and group, respectively, such that”
- Also stated in: § 3 Invariance of Parallel Trends · plain
“Proposition 3.2 shows that parallel trends of CDFs is satisfied if and only if the untreated potential outcomes for each group and time can be represented as a mixture of a common time-varying distribution that does not depend on group (with weight θ ) and a group-specific distribution that does not depend on time (with weight 1 θ ).”
plainn = 3- 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.
- Rests on an assumption not shown here.
- Also stated in: § 3 Invariance of Parallel Trends · plain
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This is in fact a sharp testable implication, since the right-hand side of (7) is guaranteed to be right-continuous and to have limits of 0 and 1 as y 8 from the properties of the CDFs in the linear combination.”
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.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the parallel trends assumption holds under all strictly monotonic transformations of the outcome if and only if a stronger 'parallel trends'-type condition holds for the cumulative distribution function of untreated potential outcomes.”
- Also stated in: § 1 Introduction · plain
“First, we show that parallel trends is insensitive to functional form if and only if a 'parallel trends'-type condition holds for the entire cumulative distribution function (CDF) of Y p 0 q .”
- Also stated in: § 3 Invariance of Parallel Trends · plain
“Proposition 3.1 shows that parallel trends is invariant to transformations if and only if a 'parallel trends'-type assumption holds for the CDFs of the untreated potential outcomes.”
plainstates an associationn = 3- 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.
- Also stated in: § 1 Introduction · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Using such tests, we are able to reject the null hypothesis that all of the implied densities are positive ( p 0 . 001 ).”
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.
12 more claims
Create a free account to see all 25 claims and to verify the 1 reference still open.
- Probably not a substantial claim. 2
- It may state two separate claims as one. 6
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For example, if the parallel trends assumption holds in the outcome variable’s original levels, it will generally not hold in log-transformed levels (for other transformations, see [67, 68]), unless there was randomization of treatment and/or no differential time trends [32].”
From Difference-in-Differences for Health Policy and Practice: A Review of Modern Methods (2025) · cites this paper as [32]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Where formal theory is well-developed, researchers may be able to translate the parallel trends assumption into domain-specific conditions and use context to help select functional form or scale of the outcome, to which the parallel trends assumption is usually sensitive [17, 32, 66].”
From Difference-in-Differences for Health Policy and Practice: A Review of Modern Methods (2025) · cites this paper as [32]
Citations
Cites
The Effect of Minimum Wages on Low-Wage Jobs*
Cengiz, D., Dube, A., Lindner, A., & Zipperer, B. (2019) · The Quarterly Journal of Economics · doi:10.1093/qje/qjz014 · Cited by 2,688
Semiparametric Difference-in-Differences Estimators
Abadie, A. (2005) · The Review of Economic Studies · doi:10.1111/0034-6527.00321 · Cited by 2,286
What's Trending in Difference-in-Differences? A Synthesis of the Recent Econometrics Literature
Roth, J., Sant'Anna, P. H. C., Bilinski, A., & Poe, J. (2022) · arXiv · Cited by 2,036
Self-citationNatural and Quasi- Experiments in Economics
Meyer, B. (1994) · Journal of Business and Economic Statistics · doi:10.2307/1392369 · Cited by 1,792
Natural and Quasi-Experiments in Economics
Meyer, B. D. (1995) · Journal of Business & Economic Statistics · doi:10.1080/07350015.1995.10524589 · Cited by 1,100
Identification and Inference in Nonlinear Difference-in-Differences Models
Athey, S., & Imbens, G. W. (2006) · Econometrica · doi:10.1111/j.1468-0262.2006.00668.x · Cited by 1,084
Doubly robust difference-in-differences estimators
Sant’Anna, P. H. C., & Zhao, J. (2020) · Journal of Econometrics · doi:10.1016/j.jeconom.2020.06.003 · Cited by 1,047 · cited 1×
“Our results thus have implications for the conditional parallel trends assumptions considered in, for example, Abadie (2005) and Sant’Anna and Zhao (2020).”
ResultSelf-citationDesign-based analysis in Difference-In-Differences settings with staggered adoption
Athey, S., & Imbens, G. W. (2022) · Journal of Econometrics · doi:10.1016/j.jeconom.2020.10.012 · Cited by 917
Inside the War on Poverty: The Impact of Food Stamps on Birth Outcomes
Almond, D., Hoynes, H. W., & Schanzenbach, D. W. (2011) · Review of Economics and Statistics · doi:10.1162/rest_a_00089 · Cited by 547
Kahn-Lang, A., & Lang, K. (2020) · Journal of Business & Economic Statistics · doi:10.1080/07350015.2018.1546591 · Cited by 367
Inference in Regression Discontinuity Designs with a Discrete Running Variable
Kolesár, M., & Rothe, C. (2018) · American Economic Review · doi:10.1257/aer.20160945 · Cited by 269
Manski, C. F., & Pepper, J. V. (2018) · Review of Economics and Statistics · doi:10.1162/rest_a_00689 · Cited by 158
Optimal Inference in a Class of Regression Models
Armstrong, T. B., & Kolesár, M. (2018) · Econometrica · doi:10.3982/ecta14434 · Cited by 120
Quantile treatment effects in difference in differences models with panel data
Callaway, B., & Li, T. (2019) · Quantitative Economics · doi:10.3982/qe935 · Cited by 110 · cited 4×
“Our work relates to several papers that consider identification of quantile treatment effects in difference-in-differences settings (Athey and Imbens, 2006; Bonhomme and Sauder, 2011; Callaway and Li, 2019). These papers introduce new sets of assumptions that differ from the usual parallel trends assumption and allow…”
InfluentialPractical and Theoretical Advances in Inference for Partially Identified Models
Canay, I. A., & Shaikh, A. M. (2017) · Cambridge University Press eBooks · doi:10.1017/9781108227223.009 · Cited by 106
Cengiz, D., Dubé, A., Lindner, A., & Zipperer, B. (2019) · National Bureau of Economic Research · doi:10.3386/w25434 · Cited by 81
The Effects of Collective Bargaining Rights on Public Employee Compensation
Frandsen, B. (2015) · Industrial and Labor Relations Review · doi:10.1177/0019793915603068 · Cited by 61
Bonhomme, S., & Sauder, U. (2011) · Review of Economics and Statistics · doi:10.1162/rest_a_00164 · Cited by 58
American Economic Review: Insights
Finkelstein, A. N. (2021) · AEA Papers and Proceedings · doi:10.1257/pandp.111.686 · Cited by 57
Bias‐Aware Inference in Fuzzy Regression Discontinuity Designs
Noack, C., & Rothe, C. (2024) · Econometrica · doi:10.3982/ecta19466 · Cited by 52
When Is Parallel Trends Sensitive to Functional Form?Preprint
Roth, J., & Sant’Anna, P. H. C. (2020) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2010.04814 · Cited by 43
Self-citationDesign-Based Uncertainty for Quasi-Experiments
Rambachan, A., & Roth, J. (2025) · Journal of the American Statistical Association · doi:10.1080/01621459.2025.2526700 · Cited by 26
Self-citationPractical and theoretical advances in inference for partially identified models
Canay, I. A., & Shaikh, A. M. (2017) · doi:10.1920/wp.cem.2016.0516 · Cited by 18
DRDID: Doubly Robust Difference-in-Differences Estimators
Sant’Anna, P. H. C., & Zhao, J. B. (2020) · doi:10.32614/cran.package.drdid · Cited by 6
Self-citationReplication data for: Inside the War on Poverty: The Impact of Food Stamps on Birth Outcomes
Almond, D. V., Hoynes, H. W., & Schanzenbach, D. W. (2012) · Harvard Dataverse · doi:10.7910/dvn/y9r8sf
Cited by
Revisiting Event-Study Designs: Robust and Efficient Estimation
Borusyak, K., Jaravel, X., & Spiess, J. (2024) · Review of Economic Studies · doi:10.1093/restud/rdae007 · Cited by 2,280
What's trending in difference-in-differences? A synthesis of the recent econometrics literature
Roth, J., Sant’Anna, P. H. C., Bilinski, A., & Poe, J. (2023) · Journal of Econometrics · doi:10.1016/j.jeconom.2023.03.008 · Cited by 2,027
Self-citationLogs with Zeros? Some Problems and Solutions
Chen, J., & Roth, J. (2024) · The Quarterly Journal of Economics · doi:10.1093/qje/qjad054 · Cited by 970
Self-citationHow Much Should We Trust Staggered Difference-In-Differences Estimates?
Baker, A., Larcker, D. F., & Wang, C. C. Y. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3794018 · Cited by 670
Advances in Difference-in-differences Methods for Policy Evaluation Research
Wang, G., Hamad, R., & White, J. S. (2024) · Epidemiology · doi:10.1097/ede.0000000000001755 · Cited by 117
“21 Recently, more sophisticated tests of parallel pretrends have been proposed, 22,23 to address potential problems associated with using event studies to test pretrends (discussed later).”
Metadata
- Authors
- Roth, J., & Sant'Anna, P. H. C.
- Affiliations
- Brown University (US)
- Microsoft Research
- Venue
- Econometrica
- Publisher
- The Econometric Society
- Published
- 2023
- Volume
- 91
- Issue
- 2
- Pages
- 737-747
- ISSN
- 0012-9682 (ISSN-L)
- OpenAlex
- W3091865267
- Semantic Scholar
- 16e842f352e81bbdd28f01b63e4f37e7eb962bde
- Cited by
- 142
- References
- 20
- Citations by year
- 2026: 35 · 2025: 46 · 2024: 31 · 2023: 23
- FWCI
- 27.39
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Econometrica (publishedVersion)
- 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
- Social Sciences › Public Administration › Evaluation and Performance Assessment
- Keywords
- parallel trends assumption, difference-in-differences, monotone transformations, cumulative distribution function, falsification tests, random assignment, treatment effects
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 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
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.