Why High-order Polynomials Should not be Used in Regression Discontinuity Designs

Andrew Gelman, Guido Imbens

It is common in regression discontinuity analysis to control for high order (third, fourth, or higher) polynomials of the forcing variable. We argue that estimators for causal effects based on such methods can be misleading, and we recommend researchers do not use them, and instead use estimators based on local linear or quadratic polynomials or other smooth functions

MoreLess

Year of publication:	August 2014
Authors:	Gelman, Andrew
Other Persons:	Imbens, Guido (contributor)
Institutions:	National Bureau of Economic Research (contributor)
Publisher:	Cambridge, Mass : National Bureau of Economic Research
Subject:	Regressionsanalyse \| Regression analysis \| Schätztheorie \| Estimation theory

freely available

Full text |

More access options

doi.org

Check Google Scholar

In German libraries (KVK)

I need help

Extent:	1 Online-Ressource
Series:	NBER working paper series ; no. w20405
Type of publication:	Book / Working Paper
Language:	English
Notes:	Mode of access: World Wide Web System requirements: Adobe [Acrobat] Reader required for PDF files Hardcopy version available to institutional subscribers.
Other identifiers:	10.3386/w20405 [DOI]
Source:	ECONIS - Online Catalogue of the ZBW

Persistent link: https://www.econbiz.de/10012458261