Scrutinizing the Monotonicity Assumption in IV and fuzzy RD designs*

Fiorini, M; Stevens, K

Scrutinizing the Monotonicity Assumption in IV and fuzzy RD designs*

Fiorini, M

Stevens, K

Permalink

Publisher:: Wiley
Publication Type:: Journal Article
Citation:: Oxford Bulletin of Economics and Statistics, 2021, 83, (6), pp. 1475-1526
Issue Date:: 2021-12-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 1 Dec 2023

Adobe PDF

Download Accepted versionAdobe PDF (1.16 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Fiorini, M https://orcid.org/0000-0002-0496-6940
dc.contributor.author	Stevens, K
dc.date.accessioned	2022-02-20T05:44:13Z
dc.date.available	2022-02-20T05:44:13Z
dc.date.issued	2021-12-01
dc.identifier.citation	Oxford Bulletin of Economics and Statistics, 2021, 83, (6), pp. 1475-1526
dc.identifier.issn	0305-9049
dc.identifier.issn	1468-0084
dc.identifier.uri	http://hdl.handle.net/10453/154702
dc.description.abstract	Whenever treatment effects are heterogeneous, and there is sorting into treatment based on the gain, monotonicity is a condition that both instrumental variable (IV) and fuzzy regression discontinuity (RD) designs must satisfy for their estimate to be interpretable as a local average treatment effect. However, applied economic work often omits a discussion of this important assumption. A possible explanation for this missing step is the lack of a clear framework to think about monotonicity in practice. In this paper, we use an extended Roy model to provide insights into the interpretation of IV and fuzzy RD estimates under various degrees of treatment effect heterogeneity, sorting on gain and violation of monotonicity. We then extend our analysis to two applied settings to illustrate how monotonicity can be investigated using a mix of economic insights, data patterns and formal tests. For both settings, we use a Roy model to interpret the estimate even in the absence of monotonicity. We conclude with a set of recommendations for the applied researcher.
dc.language	en
dc.publisher	Wiley
dc.relation.ispartof	Oxford Bulletin of Economics and Statistics
dc.relation.isbasedon	10.1111/obes.12430
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject	14 Economics
dc.subject.classification	Economics
dc.title	Scrutinizing the Monotonicity Assumption in IV and fuzzy RD designs*
dc.type	Journal Article
utslib.citation.volume	83
utslib.for	14 Economics
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Business
pubs.organisational-group	/University of Technology Sydney/Faculty of Business/Economics Discipline
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2023-12-01T00:00:00+1000Z
dc.date.updated	2022-02-20T05:44:12Z
pubs.issue	6
pubs.publication-status	Published
pubs.volume	83
utslib.citation.issue	6

Abstract:

Whenever treatment effects are heterogeneous, and there is sorting into treatment based on the gain, monotonicity is a condition that both instrumental variable (IV) and fuzzy regression discontinuity (RD) designs must satisfy for their estimate to be interpretable as a local average treatment effect. However, applied economic work often omits a discussion of this important assumption. A possible explanation for this missing step is the lack of a clear framework to think about monotonicity in practice. In this paper, we use an extended Roy model to provide insights into the interpretation of IV and fuzzy RD estimates under various degrees of treatment effect heterogeneity, sorting on gain and violation of monotonicity. We then extend our analysis to two applied settings to illustrate how monotonicity can be investigated using a mix of economic insights, data patterns and formal tests. For both settings, we use a Roy model to interpret the estimate even in the absence of monotonicity. We conclude with a set of recommendations for the applied researcher.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/154702