EconBase
← All papers

Linear Regression in a Nonlinear World

Nadav Kunievsky

arXiv 15 Dec 2025 · Econometrics

arXiv:2512.13645 · PDF · DOI · OpenAlex · Extracted main text

Abstract

The interpretation of coefficients from multivariate linear regression relies on the assumption that the conditional expectation function is linear in the variables. However, in many cases the underlying data generating process is nonlinear. This paper examines how to interpret regression coefficients under nonlinearity. We show that if the relationships between the variable of interest and other covariates are linear, then the coefficient on the variable of interest represents a weighted average of the derivatives of the outcome conditional expectation function with respect to the variable of interest. If these relationships are nonlinear, the regression coefficient becomes biased relative to this weighted average. We show that this bias is interpretable, analogous to the biases from measurement error and omitted variable bias under the standard linear model.

Citation extraction

25
references
37
in-text mentions
25
distinct cited
0
self-citations
7,255
main-text words

appendix boundary found by appendix_command · 71% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Shlomo Yitzhaki (1996) On using linear regressions in welfare economics0.81142100%
2Joshua D. Angrist and Alan B. Krueger (1999) Empirical strategies in labor economics0.64422100%
3Joshua D. Angrist and Jörn-Steffen Pischke (2009) Mostly Harmless Econometrics: An Empiricist's Companion0.64422100%
4Christine Blandhol, John Bonney, Magne Mogstad, and Alexander Torgov… (2022) When is tsls actually late?0.64422100%
5Jeffrey M. Wooldridge (2015) Introductory Econometrics: A Modern Approach0.64422100%
6Edward H. Kennedy (2024) Semiparametric doubly robust targeted double machine learning: A review0.5112250%
7Whitney K. Newey and Thomas M. Stoker (1993) Efficiency of weighted average derivative estimators and index models0.5112250%
8Aad W. van der Vaart (1998) Asymptotic Statistics, volume 3 of Cambridge Series in Statistical and Probabilistic Mathematics0.5112250%
9Scott Cunningham (2021) Causal Inference: The Mixtape0.51121100%
10Shoya Ishimaru (2024) Empirical decomposition of the iv-ols gap with heterogeneous and nonlinear effects0.51121100%

Showing the top 10 of 25 scored citations.