With or Without U? The Appropriate Test for a U-Shaped Relationship*

2009/08/31 by Jo Thori Lind, Halvor Mehlum · 3 citations
Economics, Econometrics and Finance · #Economic Theory and Institutions #Economic theories and models

paper · pdf · doi:10.1111/j.1468-0084.2009.00569.x

openalex publication_date 2009/08/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

Nonlinear relationships are common in economic theory, and such relationships are also frequently tested empirically. We argue that the usual test of nonlinear relationships is flawed and derive the appropriate test for a U-shaped relationship. Our test gives the exact necessary and sufficient conditions for the test of a U shape in finite samples in a large class of models.

Cited by

• When Algorithms Manage Humans: A Double Machine Learning Approach to Estimating Nonlinear Effects of Algorithmic Control on Gig Worker Performance and Wellbeing
• Board of Directors and Initial Public Offerings in Unregulated Financial Markets: Evidence From Belgium a Century Ago
• Tissue Kallikrein as a Mediator in Stroke Outcomes among Patients With Metabolic Syndrome: A Multicenter Study Integrating Big Data and Biomarkers

Related

• Bounds testing approaches to the analysis of level relationships
• Inference in Econometric Models with Structural Change
• High Dimensional Tests Based on U-Statistics for Generalized Linear Models
• Testing for Nonlinear Cointegration under Heteroskedasticity
• Testing for practically significant dependencies in high dimensions via bootstrapping maxima of U-statistics