Using causal diagrams to assess parallel trends in difference-in-differences studies Article Swipe

PDF

Audrey Renson , Oliver Dukes , Zach Shahn ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2505.03526

Difference-in-differences (DID) is popular because it can allow for unmeasured confounding when the key assumption of parallel trends holds. However, there exists little guidance on how to decide a priori whether this assumption is reasonable. We attempt to develop such guidance by considering the relationship between a causal diagram and the parallel trends assumption. This is challenging because parallel trends is scale-dependent and causal diagrams are generally scale-independent. We develop conditions under which, given a nonparametric causal diagram, one can reject or fail to reject parallel trends. In particular, we adopt a linear faithfulness assumption, which states that all graphically connected variables are correlated, and which is often reasonable in practice. We show that parallel trends can be rejected if either (i) the treatment is affected by pre-treatment outcomes, or (ii) there exist unmeasured confounders for the effect of treatment on pre-treatment outcomes that are not confounders for the post-treatment outcome, or vice versa (more precisely, the two outcomes possess distinct minimally sufficient sets). We also argue that parallel trends should be strongly questioned if (iii) the pre-treatment outcomes affect the post-treatment outcomes (though the two can be correlated) since there exist reasonable semiparametric models in which such an effect violates parallel trends. When (i-iii) are absent, a necessary and sufficient condition for parallel trends is that the association between the common set of confounders and the potential outcomes is constant on an additive scale, pre- and post-treatment. These conditions are similar to, but more general than, those previously derived in linear structural equations models. We discuss our approach in the context of the effect of Medicaid expansion under the U.S. Affordable Care Act on health insurance coverage rates.

Related Topics

Truth And Reconciliation Commission Of Canada

Reich Ministry Of Public Enlightenment And Propaganda

Rick Hurst

Mutual Aid

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2505.03526
PDF: https://arxiv.org/pdf/2505.03526
OA Status: green
OpenAlex ID: https://openalex.org/W4415248492

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4415248492

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2505.03526

Digital Object Identifier
Title: Using causal diagrams to assess parallel trends in difference-in-differences studies

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-05-06

Full publication date if available
Authors: Audrey Renson, Oliver Dukes, Zach Shahn

List of authors in order
Landing page: https://arxiv.org/abs/2505.03526

Publisher landing page
PDF URL: https://arxiv.org/pdf/2505.03526

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2505.03526

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4415248492
doi	https://doi.org/10.48550/arxiv.2505.03526
ids.doi	https://doi.org/10.48550/arxiv.2505.03526
ids.openalex	https://openalex.org/W4415248492
fwci
type	preprint
title	Using causal diagrams to assess parallel trends in difference-in-differences studies
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10845
topics[0].field.id	https://openalex.org/fields/26
topics[0].field.display_name	Mathematics
topics[0].score	0.5198000073432922
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/2613
topics[0].subfield.display_name	Statistics and Probability
topics[0].display_name	Advanced Causal Inference Techniques
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2505.03526
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license	cc-by-sa
locations[0].pdf_url	https://arxiv.org/pdf/2505.03526
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id	https://openalex.org/licenses/cc-by-sa
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2505.03526
locations[1].id	doi:10.48550/arxiv.2505.03526
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2505.03526
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5030609254
authorships[0].author.orcid	https://orcid.org/0000-0003-1603-2587
authorships[0].author.display_name	Audrey Renson
authorships[0].author_position	first
authorships[0].raw_author_name	Renson, Audrey
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5079508409
authorships[1].author.orcid	https://orcid.org/0000-0002-9145-3325
authorships[1].author.display_name	Oliver Dukes
authorships[1].author_position	middle
authorships[1].raw_author_name	Dukes, Oliver
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5042387576
authorships[2].author.orcid	https://orcid.org/0000-0003-1014-8837
authorships[2].author.display_name	Zach Shahn
authorships[2].author_position	last
authorships[2].raw_author_name	Shahn, Zach
authorships[2].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2505.03526
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-16T00:00:00
display_name	Using causal diagrams to assess parallel trends in difference-in-differences studies
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10845
primary_topic.field.id	https://openalex.org/fields/26
primary_topic.field.display_name	Mathematics
primary_topic.score	0.5198000073432922
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/2613
primary_topic.subfield.display_name	Statistics and Probability
primary_topic.display_name	Advanced Causal Inference Techniques
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2505.03526
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license	cc-by-sa
best_oa_location.pdf_url	https://arxiv.org/pdf/2505.03526
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id	https://openalex.org/licenses/cc-by-sa
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2505.03526
primary_location.id	pmh:oai:arXiv.org:2505.03526
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license	cc-by-sa
primary_location.pdf_url	https://arxiv.org/pdf/2505.03526
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id	https://openalex.org/licenses/cc-by-sa
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2505.03526
publication_date	2025-05-06
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	28, 46, 74, 91, 207
abstract_inverted_index.In	87
abstract_inverted_index.We	35, 68, 111, 164, 255
abstract_inverted_index.an	198, 232
abstract_inverted_index.be	117, 171, 187
abstract_inverted_index.by	41, 126
abstract_inverted_index.if	119, 174
abstract_inverted_index.in	109, 195, 250, 259
abstract_inverted_index.is	2, 33, 55, 60, 106, 124, 215, 229
abstract_inverted_index.it	5
abstract_inverted_index.of	15, 138, 223, 262, 265
abstract_inverted_index.on	24, 140, 231, 274
abstract_inverted_index.or	81, 129, 151
abstract_inverted_index.to	26, 37, 83
abstract_inverted_index.we	89
abstract_inverted_index.(i)	121
abstract_inverted_index.Act	273
abstract_inverted_index.all	98
abstract_inverted_index.and	49, 62, 104, 209, 225, 236
abstract_inverted_index.are	65, 102, 144, 205, 240
abstract_inverted_index.but	243
abstract_inverted_index.can	6, 79, 116, 186
abstract_inverted_index.for	8, 135, 147, 212
abstract_inverted_index.how	25
abstract_inverted_index.key	13
abstract_inverted_index.not	145
abstract_inverted_index.one	78
abstract_inverted_index.our	257
abstract_inverted_index.set	222
abstract_inverted_index.the	12, 43, 50, 122, 136, 148, 156, 176, 180, 184, 217, 220, 226, 260, 263, 269
abstract_inverted_index.to,	242
abstract_inverted_index.two	157, 185
abstract_inverted_index.(ii)	130
abstract_inverted_index.Care	272
abstract_inverted_index.This	54
abstract_inverted_index.U.S.	270
abstract_inverted_index.When	203
abstract_inverted_index.also	165
abstract_inverted_index.fail	82
abstract_inverted_index.more	244
abstract_inverted_index.pre-	235
abstract_inverted_index.show	112
abstract_inverted_index.such	39, 197
abstract_inverted_index.that	97, 113, 143, 167, 216
abstract_inverted_index.this	31
abstract_inverted_index.vice	152
abstract_inverted_index.when	11
abstract_inverted_index.(DID)	1
abstract_inverted_index.(iii)	175
abstract_inverted_index.(more	154
abstract_inverted_index.These	238
abstract_inverted_index.adopt	90
abstract_inverted_index.allow	7
abstract_inverted_index.argue	166
abstract_inverted_index.exist	132, 191
abstract_inverted_index.given	73
abstract_inverted_index.often	107
abstract_inverted_index.since	189
abstract_inverted_index.than,	246
abstract_inverted_index.there	20, 131, 190
abstract_inverted_index.those	247
abstract_inverted_index.under	71, 268
abstract_inverted_index.versa	153
abstract_inverted_index.which	95, 105, 196
abstract_inverted_index.affect	179
abstract_inverted_index.causal	47, 63, 76
abstract_inverted_index.common	221
abstract_inverted_index.decide	27
abstract_inverted_index.effect	137, 199, 264
abstract_inverted_index.either	120
abstract_inverted_index.exists	21
abstract_inverted_index.health	275
abstract_inverted_index.holds.	18
abstract_inverted_index.linear	92, 251
abstract_inverted_index.little	22
abstract_inverted_index.models	194
abstract_inverted_index.priori	29
abstract_inverted_index.rates.	278
abstract_inverted_index.reject	80, 84
abstract_inverted_index.scale,	234
abstract_inverted_index.sets).	163
abstract_inverted_index.should	170
abstract_inverted_index.states	96
abstract_inverted_index.trends	17, 52, 59, 115, 169, 214
abstract_inverted_index.which,	72
abstract_inverted_index.(i-iii)	204
abstract_inverted_index.(though	183
abstract_inverted_index.absent,	206
abstract_inverted_index.attempt	36
abstract_inverted_index.because	4, 57
abstract_inverted_index.between	45, 219
abstract_inverted_index.context	261
abstract_inverted_index.derived	249
abstract_inverted_index.develop	38, 69
abstract_inverted_index.diagram	48
abstract_inverted_index.discuss	256
abstract_inverted_index.general	245
abstract_inverted_index.models.	254
abstract_inverted_index.popular	3
abstract_inverted_index.possess	159
abstract_inverted_index.similar	241
abstract_inverted_index.trends.	86, 202
abstract_inverted_index.whether	30
abstract_inverted_index.However,	19
abstract_inverted_index.Medicaid	266
abstract_inverted_index.additive	233
abstract_inverted_index.affected	125
abstract_inverted_index.approach	258
abstract_inverted_index.constant	230
abstract_inverted_index.coverage	277
abstract_inverted_index.diagram,	77
abstract_inverted_index.diagrams	64
abstract_inverted_index.distinct	160
abstract_inverted_index.guidance	23, 40
abstract_inverted_index.outcome,	150
abstract_inverted_index.outcomes	142, 158, 178, 182, 228
abstract_inverted_index.parallel	16, 51, 58, 85, 114, 168, 201, 213
abstract_inverted_index.rejected	118
abstract_inverted_index.strongly	172
abstract_inverted_index.violates	200
abstract_inverted_index.condition	211
abstract_inverted_index.connected	100
abstract_inverted_index.equations	253
abstract_inverted_index.expansion	267
abstract_inverted_index.generally	66
abstract_inverted_index.insurance	276
abstract_inverted_index.minimally	161
abstract_inverted_index.necessary	208
abstract_inverted_index.outcomes,	128
abstract_inverted_index.potential	227
abstract_inverted_index.practice.	110
abstract_inverted_index.treatment	123, 139
abstract_inverted_index.variables	101
abstract_inverted_index.Affordable	271
abstract_inverted_index.assumption	14, 32
abstract_inverted_index.conditions	70, 239
abstract_inverted_index.precisely,	155
abstract_inverted_index.previously	248
abstract_inverted_index.questioned	173
abstract_inverted_index.reasonable	108, 192
abstract_inverted_index.structural	252
abstract_inverted_index.sufficient	162, 210
abstract_inverted_index.unmeasured	9, 133
abstract_inverted_index.association	218
abstract_inverted_index.assumption,	94
abstract_inverted_index.assumption.	53
abstract_inverted_index.challenging	56
abstract_inverted_index.confounders	134, 146, 224
abstract_inverted_index.confounding	10
abstract_inverted_index.considering	42
abstract_inverted_index.correlated)	188
abstract_inverted_index.correlated,	103
abstract_inverted_index.graphically	99
abstract_inverted_index.particular,	88
abstract_inverted_index.reasonable.	34
abstract_inverted_index.faithfulness	93
abstract_inverted_index.relationship	44
abstract_inverted_index.nonparametric	75
abstract_inverted_index.pre-treatment	127, 141, 177
abstract_inverted_index.post-treatment	149, 181
abstract_inverted_index.semiparametric	193
abstract_inverted_index.post-treatment.	237
abstract_inverted_index.scale-dependent	61
abstract_inverted_index.scale-independent.	67
abstract_inverted_index.Difference-in-differences	0
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	3
citation_normalized_percentile