Why High-Order Polynomials Should Not Be Used in Regression Discontinuity Designs. A Comment on Gelman and Imbens (Journal of Business & Economic Statistics, 2019)

Melle R. Albada

Journal of Comments and Replications in Economics (JCRE), 2025, vol. 4, No 2025-11, 16 pages

Abstract: Gelman and Imbens (2019) argue against using global high-order polynomial models in regression discontinuity designs, recommending local linear or quadratic models instead. This comment revisits two of their arguments, showing they are contingent on specific contexts and interpretations. First, global high-order polynomial models assign extreme weights when the running variable's distribution has regions with few observations. Because so few observations receive these weights, their contribution to the treatment estimate is usually small. Second, I establish that local models can also yield excessive false positive findings, even when using best-practice modeling methods, and that this problem worsens as the sample size grows. These results improve our understanding of the limitations of global high-order polynomial models and suggest that researchers should routinely investigate false positive rates in their study.

Keywords: Local polynomial regression; Treatment effect estimation; Policy analysis; False positives (search for similar items in EconPapers)
JEL-codes: C14 C15 C18 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/337525/1/JCRE-2025-11.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:zbw:jcreco:337525

DOI: 10.18718/81781.50

Access Statistics for this article

Journal of Comments and Replications in Economics (JCRE) is currently edited by David A. Jaeger, Maren Duvendack, W. Robert Reed

More articles in Journal of Comments and Replications in Economics (JCRE) from ZBW - Leibniz Information Centre for Economics Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().